US20140081768A1

US20140081768A1 - Recommendation machine

Info

Publication number: US20140081768A1
Application number: US14/025,616
Authority: US
Inventors: Samuel Mcmillian Hocking, JR.; Thomas Johannes Oberlechner; Edward Casteel Milner; Peter R. Paradis; Julia Pitters
Original assignee: iMATCHATIVE Corp
Current assignee: ADDEPAR Inc
Priority date: 2012-09-15
Filing date: 2013-09-12
Publication date: 2014-03-20
Also published as: US20150199746A1; US20160171609A1; US10181158B2

Abstract

A machine may be configured as a recommendation machine that makes one or more recommendations to one or more users. The machine may provide a recommendation based on one or more psychometric profiles that correspond to a user, a product, a manager for the product, or any suitable combination thereof. The user may be a potential buyer of the product, and the manager for the product may fully or partially manage the product and consequently affect the value of the product. The user's psychometric profile may describe market understanding and risk tolerance possessed by the user, and the manager's psychometric profile may describe market understanding and risk tolerance held by the manager. Such psychometric profiles may be used to make recommendations of products. In addition, a psychometric profile for the product itself may be used in the making of such recommendations.

Description

RELATED APPLICATIONS

This application claims the priority benefits of U.S. Provisional Patent Application No. 61/743,930, filed Sep. 15, 2012, and U.S. Provisional Patent Application No. 61/829,146, filed May 30, 2013, both of which are incorporated herein by reference in their entirety.

TECHNICAL FIELD

The subject matter disclosed herein generally relates to the processing of data. Specifically, the present disclosure addresses systems and methods to facilitate making recommendations.

BACKGROUND

A product may be available for purchase from a seller. A product may take the form of a good (e.g., a physical object), a service (e.g., performed by a service provider), information (e.g., downloadable digital media), a license (e.g., authorization to access something or do something), or any suitable combination thereof. An item may be a specimen (e.g., an individual instance) of the product, and multiple items may constitute multiple specimens of the product. A machine may be configured (e.g., by special software) to provide a user with a recommendation of a product of which one or more specimens may be available for to purchase. Such a machine may form all or part of a network-based system. Examples of network-based systems include commerce systems (e.g., systems that host shopping websites or auction websites), publication systems (e.g., systems that host classified advertisement websites), listing systems (e.g., systems that host wish list websites or gift registries), transaction systems (e.g., systems that host payment websites), and social network systems (e.g., Facebook®, Twitter®, or LinkedIn®).

BRIEF DESCRIPTION OF THE DRAWINGS

Some embodiments are illustrated by way of example and not limitation in the figures of the accompanying drawings.

FIG. 1 is a network diagram illustrating a network environment suitable for a recommendation machine, according to some example embodiments.

FIG. 2 is a block diagram illustrating components of a recommendation machine suitable for making recommendations, according to some example embodiments.

FIG. 3 is a conceptual diagram illustrating relationships among a user, a product, and a manager of the product, as well as their associated psychometric profiles, according to some example embodiments.

FIG. 4 is a conceptual diagram illustrating the relationships depicted in FIG. 3, as applied to groups of multiple users and groups of multiple managers, according some example embodiments.

FIG. 5 is a conceptual diagram illustrating generation of psychometric profiles for one or more persons, such as a user or a manager, according to some example embodiments.

FIG. 6 is a conceptual diagram illustrating generation of a psychometric profile for a product, according to some example embodiments.

FIG. 7 is a block diagram illustrating a psychometric profile, according to some example embodiments.

FIG. 8-15 are flowcharts illustrating operations of the recommendation machine in performing a method of making a recommendation, according to some example embodiments.

FIG. 16 is a screenshot illustrating a user interface with parameter selection sliders, according to some example embodiments.

FIG. 17 is a block diagram illustrating components of a machine, according to some example embodiments, able to read instructions from a machine-readable medium and perform any one or more of the methodologies discussed herein.

DETAILED DESCRIPTION

Example methods and systems are directed to identification of one or more media sources. Examples merely typify possible variations. Unless explicitly stated otherwise, components and functions are optional and may be combined or subdivided, and operations may vary in sequence or be combined or subdivided. In the following description, for purposes of explanation, numerous specific details are set forth to provide a thorough understanding of example embodiments. It will be evident to one skilled in the art, however, that the present subject matter may be practiced without these specific details.
A machine may be configured (e.g., by special software) as a recommendation machine that makes one or more recommendations. The machine may form all or part of a network-based recommendation system configured to provide one or more recommendation services that make recommendations to one or more users. For clarity, example embodiments of the machine are described herein in the context of making recommendations of financial products, such as hedge funds, though other example embodiments of the machine may be configured to perform similar operations for making recommendations of other products. The machine may provide a recommendation based on one or more psychometric profiles that correspond to a user, a product, a manager for the product, or any suitable combination thereof. Where the product is a financial product (e.g., an investment fund, such as a hedge fund), the user may be a person or group of persons (e.g., a team or a company) acting as a potential buyer of the product (e.g., as a prospective investor in the hedge fund). The manager for the product may be a person or group of persons that fully or partially manages the product and whose decisions may affect the value of the product (e.g., increase or decrease the value of the hedge fund).
A psychometric profile includes (e.g., contains) market model, risk model, or both. The market model describes the market for the product, including an implicit or unconscious psychological understanding of the market. The risk model indicates an implicit or unconscious psychological preference for risk tolerance (e.g., risk-taking or safety-seeking) Hence, the user's psychometric profile may describe market understanding and risk tolerance possessed by the user, and the manager's psychometric profile may describe market understanding and risk tolerance held by the manager. Such psychometric profiles may be generated, stored, and accessed by the recommendation machine, and used to make recommendations of products (e.g., financial products, such as hedge funds). In addition, a psychometric profile (e.g., a quasi-psychometric profile) for the product itself may be generated, stored, and accessed by the recommendation machine, and used in the making of such recommendations.
FIG. 1 is a network diagram illustrating a network environment 100 suitable for a recommendation machine 110, according to some example embodiments. The network environment 100 includes the recommendation machine 110, a database 115, and devices 130 and 150, all communicatively coupled to each other via a network 190. The recommendation machine 110, the database 115, and the devices 130 and 150 may each be implemented in a computer system, in whole or in part, as described below with respect to FIG. 17. As shown, the recommendation machine 110, with or without the database 115, may form all or part of a network-based system 105 (e.g., a cloud-based product recommendation system, such as a cloud-based financial product recommendation system).
Also shown in FIG. 1 are users 132 and 152. One or both of the users 132 and 152 may be a human user (e.g., a human being) or a combination of a human user and a machine (e.g., a human assisted by a machine or a machine supervised by a human, locally or remotely). The user 132 is not part of the network environment 100, but is associated with the device 130 and may be a user of the device 130. For example, the device 130 may be a desktop computer, a vehicle computer, a tablet computer, a navigational device, a portable media device, or a smart phone belonging to the user 132. Likewise, the user 152 is not part of the network environment 100, but is associated with the device 150. As an example, the device 150 may be a desktop computer, a vehicle computer, a tablet computer, a navigational device, a portable media device, or a smart phone belonging to the user 152.
Any of the machines, databases, or devices shown in FIG. 1 may be implemented in a general-purpose computer modified (e.g., configured or programmed) by special software to be a special-purpose computer to perform one or more of the functions described herein for that machine, database, or device. For example, a computer system able to implement any one or more of the methodologies described herein, in full or in part, is discussed below with respect to FIG. 17. As used herein, a “database” is a data storage resource and may store data structured as a text file, a table, a spreadsheet, a relational database (e.g., an object-relational database), a triple store, a hierarchical data store, or any suitable combination thereof. Moreover, any two or more of the machines, databases, or devices illustrated in FIG. 1 may be combined into a single machine, and the functions described herein for any single machine, database, or device may be subdivided among multiple machines, databases, or devices.
The network 190 may be any network that enables communication between or among machines, databases, and devices (e.g., the server machine 110 and the device 130). Accordingly, the network 190 may be a wired network, a wireless network (e.g., a mobile or cellular network), or any suitable combination thereof. The network 190 may include one or more portions that constitute a private network, a public network (e.g., the Internet), or any suitable combination thereof. Accordingly, the network 190 may include one or more portions that incorporate a local area network (LAN), a wide area network (WAN), the Internet, a mobile telephone network (e.g., a cellular network), a wired telephone network (e.g., a plain old telephone system (POTS) network), a wireless data network (e.g., WiFi network or WiMax network), or any suitable combination thereof. Any one or more portions of the network 190 may communicate information via a transmission medium. As used herein, “transmission medium” shall be taken to include any intangible medium that is capable of storing, encoding, or carrying instructions for execution by a machine, and includes digital or analog communication signals or other intangible media to facilitate communication of such software.
FIG. 2 is a block diagram illustrating components of the recommendation machine 110, according to some example embodiments. The recommendation machine 110 is shown as including an access module 210, a user interface module 220, the user analysis module 230, a product analysis module 240, and a recommender module 280, all configured to communicate with each other (e.g., via a bus, shared memory, or a switch).
The access module 210 may be configured to access information from various sources, such as the database 115, the device 130, the device 150, or any suitable combination thereof. The user interface module 220 may be configured to cause a user interface (e.g., the user interface of an application or app executing on the client device 130) to present a reference to a product (e.g., a search result, a report, or an advertisement that references the product. Such a reference may be a recommendation of the product, may function as a recommendation of the product, and may be presented as a recommendation of the product.
As shown in FIG. 2, the user analysis module 230 may include a market metaphor module 232, risk module 234, and a group module 236, all configured to communicate with each other. The risk module 234 is shown as including an implicit association module 235. In the context of recommending financial products (e.g., hedge funds), the users 132 and 152 may be treated as potential or actual investors, and the user analysis module 230 may be configured as an investor analysis module.
Similarly, the product analysis module 240 may include a market metaphor module 242, risk module 244, and a group module 246, all configured to communicate with each other. The risk module 244 is shown as including an implicit association module 245. In the context of recommending financial products (e.g., investments), the product analysis module 240 may be configured as an investment analysis module.
The recommender module 280 is shown in FIG. 2 as including a search module 250, product match module 260, and alternative product module 270, all configured to communicate with each other. In the context of recommending financial products (e.g., investments), the search module 250 may be configured as an investment search module (e.g., for implementing an investment search engine); the product match module 260 may be configured as an investment match module (e.g., for implementing an investment matching service); and the alternative product module 270 may be configured as an alternative investment module (e.g., a recommender of alternative investments, given an initial investment as input).
Any one or more of the modules described herein may be implemented using hardware (e.g., a processor of a machine) or a combination of hardware and software. For example, any module described herein may configure a processor to perform the operations described herein for that module. Moreover, any two or more of these modules may be combined into a single module, and the functions described herein for a single module may be subdivided among multiple modules. Furthermore, according to various example embodiments, modules described herein as being implemented within a single machine, database, or device may be distributed across multiple machines, databases, or devices.
FIG. 3 is a conceptual diagram illustrating relationships among a user 310 (e.g., user 132 or user 152), a product 320 (e.g., an investment, such as a hedge fund), and a manager 330 of the product 320, as well as their associated psychometric profiles 312, 322, and 332, according to some example embodiments. As shown in FIG. 3, the user 310 may be an investor, shopper, or other potential buyer for the product 320. The manager 330 may be a person whose decisions affect the value (e.g., a market value that represents worth, such as a price) of the product 320 (e.g., a financial manager that decides when to buy and sell assets and securities within the hedge fund).
The psychometric profile 312 of the user 310 describes market understanding (e.g., unconscious) held by the user 310, indicates psychological preferences (e.g., unconscious) of the user 310 for risk tolerance (e.g., risk-taking or safety-seeking), or both. The psychometric profile 312 may be self-reported by the user 310, inferred by the recommendation machine 110 (e.g., by the user analysis module 230) based on detected behavior of the user 310, or any suitable combination thereof
Likewise, the psychometric profile 332 of the manager 330 describes market understanding (e.g., unconscious) held by the manager 330, indicates psychological preferences (e.g., unconscious) of the manager 330 for risk tolerance (e.g., risk-taking or safety-seeking), or both. The psychometric profile 332 may be self-reported by the manager 330, inferred by the recommendation machine 110 (e.g., by the product analysis module 240) based on detected behavior of the manager 330, or any suitable combination thereof
Although the product 320 is not a person, the psychometric profile 322 of the product 320 may be a quasi-psychometric profile of the product 320 itself, where the psychometric profile 322 is usable as a functional equivalent of a psychometric profile (e.g., psychometric profile 332) for a person. The psychometric profile 322 of the product 320 may describe an inferred market understanding, inferred preferences for risk tolerance, or both. The psychometric profile 322 may be inferred (e.g., approximated, estimated, or otherwise derived) by the recommendation machine 110 (e.g., by the product analysis module 240) based on statistical performance of the product 320 (e.g., statistical data describing gains, losses, sales of assets, acquisitions of assets, or any suitable combination thereof, with respect to the product 320).
FIG. 4 is a conceptual diagram illustrating the relationships depicted in FIG. 3, as applied to groups of multiple users and groups of multiple managers, according some example embodiments. As shown in the top portion of FIG. 4, a group 410 of users (e.g., an investor team) may function like a single user (e.g., user 310) with respect to researching products and shopping for products. A single psychometric profile 412 may be associated with (e.g., assigned to) the entire group 410 as a whole. Accordingly, the psychometric profile 412 may describe market understanding (e.g., unconscious) held by the group 410, indicate psychological preferences (e.g., unconscious) of the group 410 for risk tolerance (e.g., risk-taking or safety-seeking), or any suitable combination thereof. Moreover, the psychometric profile 412 may be self-reported by the group 410, inferred by the recommendation machine 110 (e.g., by the user analysis module 230) based on detected behavior of the group 410, or any suitable combination thereof
As also shown in the top portion of FIG. 4, a group 430 of managers (e.g., a management team) may function like a single manager (e.g., manager 330) with respect to managing products and making decisions that affect their value. A single psychometric profile 432 may be associated with (e.g., assigned to) the entire group 430 as a whole. Accordingly, the psychometric profile 432 may describe market understanding (e.g., unconscious) held by the group 430, indicate psychological preferences (e.g., unconscious) of the group 430 for risk tolerance (e.g., risk-taking or safety-seeking), or any suitable combination thereof. Moreover, the psychometric profile 432 may be self-reported by the group 430, inferred by the recommendation machine 110 (e.g., by the product analysis module 240) based on detected behavior of the group 430, or any suitable combination thereof
Furthermore, the top portion of FIG. 4 shows that a product 420 (e.g., an investment, such as a hedge fund) may have its own psychometric profile 422, which may be a quasi-psychometric profile of the product 420 itself. The psychometric profile 422 of the product 420 may describe an inferred market understanding, inferred preferences for risk tolerance, or both. The psychometric profile 422 may be inferred by the recommendation machine 110 (e.g., by the product analysis module 240) based on statistical performance of the product 420.
As shown in the bottom portion of FIG. 4, a user entity 460 (e.g., corporation or other business organization) may function like a single user (e.g., user 310) with respect to researching products and shopping for products. A single psychometric profile 462 may be associated with (e.g., assigned to) the entire user entity 460 as a whole. Accordingly, the psychometric profile 462 may describe market understanding (e.g., unconscious) held by the user entity 460, indicate psychological preferences (e.g., unconscious) of the user entity 460 for risk tolerance, or any suitable combination thereof. Moreover, the psychometric profile 462 may be self-reported by the user entity 460, inferred by the recommendation machine 110 (e.g., by the user analysis module 230) based on detected behavior of the user entity 460, or any suitable combination thereof
As also shown in the bottom portion of FIG. 4, a managing entity 480 (e.g., a management company) may function like a single manager (e.g., manager 330) with respect to managing products and making decisions that affect their value. A single psychometric profile 482 may be associated with (e.g., assigned to) the entire managing entity 480 as a whole. Accordingly, the psychometric profile 482 may describe market understanding (e.g., unconscious) held by the managing entity 480, indicate psychological preferences (e.g., unconscious) of the managing entity 480 for risk tolerance, or any suitable combination thereof. Moreover, the psychometric profile 482 may be self-reported by the managing entity 480, inferred by the recommendation machine 110 (e.g., by the product analysis module 240) based on detected behavior of the managing entity 480, or any suitable combination thereof
Furthermore, the bottom portion of FIG. 4 shows that a product 470 (e.g., an investment, such as a hedge fund) may have its own psychometric profile 472, which may be a quasi-psychometric profile of the product 470 itself. The psychometric profile 472 of the product 470 may describe an inferred market understanding, inferred preferences for risk tolerance, or both. The psychometric profile 472 may be inferred by the recommendation machine 110 (e.g., by the product analysis module 240) based on statistical performance of the product 470.
FIG. 5 is a conceptual diagram illustrating generation of a psychometric profile (e.g., psychometric profile 312, 332, 412, 432, 462, or 482) for one or more persons (e.g., humans), such as the user 310, the manager 330, the group 410 of users, the group 430 of managers, the user entity 460, or the manager entity 480, according to some example embodiments. As described in further detail below, generation of a psychometric profile (e.g., psychometric profile 312) may be based on one or more inputs. After generation, psychometric profiles (e.g., psychometric profile 312) may be stored in the database 115, for subsequent access therefrom (e.g., by the access module 210 of the recommendation machine 110).
As shown in FIG. 5, examples of such inputs include one or more metaphor statements, such as a metaphor statement 510, with or without its corresponding influence strength 512, and a further metaphor statement 520, with or without its corresponding influence strength 522. Other examples of such inputs include one or more implicit association test (IAT) results, such as an IAT result 530 (e.g., resulting from an IAT administered without priming) and another IAT result 540 (e.g., resulting from an IAT administered with priming).
A further example of such inputs is preferences 550 of the person for whom the psychometric profile (e.g., psychometric profile 312) is being generated. The preferences 550 may indicate, specify, define, or constrain attributes or characteristics of products. In the context of financial products (e.g., hedge funds), the preferences 550 may indicate attributes such as specific fees (e.g., a management fee, a performance fee, or a redemption fee), costs, assets (e.g., identifiers of the individual investment instruments, such as stocks, or categories thereof), an investment type (e.g., hedge fund, mutual fund, or exchange-traded fund), an investment size (e.g., expressed as a current value of all assets), an investment style (e.g., a name of an investment strategy, or a category thereof), or any suitable combination thereof.
A yet further example of such inputs is behavior data 560 of the person for whom the psychometric profile (e.g., psychometric profile 312) is being generated. The behavior data 560 may indicate, record, track, or reference historical behavior of the person. For example, the behavior data 560 may include a search history of a person, an investment history of the person, or both. As shown in FIG. 5, one or more of these inputs may be used (e.g., by the recommendation machine 110) to generate or update psychometric profiles (e.g., psychometric profiles 312, 332, 412, 432, 462, and 482), which may be stored in the database 115 for access by the recommendation machine 110.
FIG. 6 is a conceptual diagram illustrating generation of a psychometric profile (e.g., psychometric profile 322, 422, or 472) for a product (e.g., product 320, 420, or 470), according to some example embodiments. As described in further detail below, generation of a psychometric profile (e.g., psychometric profile 322, which may be a quasi-psychometric profile) correlated with a product (e.g., product 320) may be based on statistical data 610 (e.g., performance statistics) that indicates, records, tracks, or references historical events indicative of changes in the value of the product (e.g., product 320). For example, the statistical data 610 may include information about past returns (e.g., absolute returns, gains, losses, or any suitable combination thereof), fees, costs, financial ratios (e.g., Sharpe ratio), or any suitable combination thereof.
FIG. 7 is a block diagram illustrating the psychometric profile 312, according to some example embodiments. One or more of the psychometric profiles 322, 332, 412, 422, 432, 462, 472, and 482 may be structured similarly to the psychometric profile 312. The psychometric profile 312, as noted above, corresponds to the user 310 and may indicate one or more measurable psychological attributes, traits, characteristics, or propensities (e.g., including unconscious propensities) of the user 310. As shown, the psychometric profile 312 includes a market model 710 and a risk model 720, though the psychometric profile 312 may also contain additional psychological data in reference to the user 310.
The market model 710 may be or include a figurative description of a market for products (e.g., product 320). Such a description may take the form of a metaphor statement to which the user 310 has expressed agreement or to which the user 310 is likely to agree. As such, the description of the market (e.g., a metaphor statement) may be or include an implicit or unconscious psychological understanding of the market. In the context of making recommendations of financial products, examples of metaphor statements include: “investing is competing against others and trying to beat them,” “the market is rational,” “investing is like placing bets on a gamble,” “the market is a bazaar where people shop to find the best price,” “the market has a mind of its own,” “investing in the market is like navigating on ocean,” “the market can be a dangerous minefield,” and “in the market, battles are won and lost.” Accordingly, the market model 710 may indicate an implicit or unconscious characterization applied by the user 310 to the market for products.
The risk model 720 may be or include one or more IAT results (e.g., IAT results 530 and 540). The results of an IAT indicate how strongly the test-taker (e.g., the user 310) has associated various concepts in his or her mind. In the context of making financial product recommendations, such IAT results may indicate an implicit or unconscious psychological preference for a certain degree of risk tolerance (e.g., a level of risk-taking or safety-seeking) Accordingly, the risk model 720 may indicate an implicit or unconscious degree of risk that is tolerable by the user 310 (e.g., within the market for products).
FIG. 8-15 are flowcharts illustrating operations of the recommendation machine 110 in performing a method 800 of making a recommendation of a product (e.g., product 320), according to some example embodiments. Operations in the method 800 may be performed by the recommendation machine 110 (e.g., by a processor therein) using modules described above with respect to FIG. 2. As shown in FIG. 8, the method 800 may include one or more of operations 810, 820, and 830, operation 840, one or more of operations 850 and 860, and operation 870.
In operation 810, the access module 210 accesses (e.g., from the database 115) a psychometric profile (e.g., psychometric profile 312, 412, or 462) of a user (e.g., user 310, group 410, or user entity 460). For example, the access module 210 may access the psychometric profile 312 for the user 310. As noted above, the psychometric profile 312 may include the market model 710 and the risk model 720. As also noted above, the market model 710 may indicate an unconscious characterization applied by the user 310 to a market for products (e.g., products 320, 420, and 470), and the risk model 720 may indicate an unconscious degree of risk tolerable by the user 310.
In operation 820, the access module 210 accesses (e.g., from the database 115) psychometric profiles (e.g., psychometric profile 322, 422, or 472, which may be quasi-psychometric profiles) of multiple products (e.g., products 320, 420, and 470) available for recommendation, purchase, or both, within the market for products. For example, the access module 210 may access the psychometric profile 322 of the product 320, as well as additional psychometric profiles of additional products.
In operation 830, the access module 210 accesses (e.g., from the database 115) psychometric profiles (e.g., psychometric profiles 332, 432, and 482) of various managers (e.g., manager 330, group 430, or managing entity 480) for various products (e.g., products 320, 420, and 470) available for recommendation, purchase, or both, within the market for products. For example, the access module 210 may access the psychometric profile 332 of the manager 330, as well as additional psychometric profiles of additional managers for additional products.
In operation 840, the recommender module 280 performs comparisons among the psychometric profiles accessed in one or more of operations 810, 820, 830. For example, the recommender module 280 may compare the psychometric profile 312 of the user 310 with the psychometric profile 332 of the manager 330 and other psychometric profiles of other managers. As another example, the psychometric profile 312 may be compared with the psychometric profile 322 of the product 320 and other psychometric profiles of other products. These comparisons enable identification of one or more psychometric profiles (e.g., psychometric profile 322 or 332) that match or are similar to the psychometric profile 312 of the user 310, as well as identification of the products (e.g., product 320) that are correlated with (e.g., that correspond to) the matched or similar psychometric profiles.
In operation 850, the recommender module 280 (e.g., via the search module 250) identifies the product 320 as a search result, in response to a previously submitted search (e.g., search request) submitted by the user whose psychometric profile was accessed in operation 810 (e.g., user 310, group 410, or user entity 460). For example, the search may have been previously submitted by the user 310 (e.g., by the user 132 via the device 130). The product 320 may be identified as a match to search criteria submitted by the user (e.g., a product whose psychometric profile matches the search criteria, a product whose manager has a psychometric profile that matches the search criteria, or both). This identification of the product 320 may be performed based on one or more of the comparisons performed in operation 840.
In operation 860, the recommender module 280 (e.g., via the product match module 260) identifies the product 320 as a match for the user whose psychometric profile was accessed in operation 810 (e.g., user 310). The product 320 may be identified as a user-to-product match (e.g., a product whose psychometric profile exactly, closely, or sufficiently matches the psychometric profile of the user), a user-to-manager match (e.g., a product whose manager, group of managers, or managing entity has a psychometric profile that exactly, closely, or sufficiently matches a psychometric profile the user), or both. This identification of the product 320 may be likewise performed based on (e.g., by performing) one or more of the comparisons performed in operation 840.
In operation 870, the user interface module 220 causes a user interface to present a reference to the product 320 to the user whose psychometric profile was accessed in operation 810 (e.g., user 310). For example, the user interface may form all or part of an application (e.g., a browser application or other interactive software) executing on the device 130, and the user interface module 220 may cause the user interface to present the reference to the product 320 on a display of the device 130. Moreover, the reference may be presented as a recommendation of the product 320. According to various example embodiments, the reference may take the form of a search result, an advertisement, a listing, a hyperlink, a suggestion, or other notification that references the product 320 (e.g., by name or other identifier, such as a ticker symbol). Operation 870 may be performed in response to operation 850, operation 860, or any suitable combination thereof
According to some example embodiments, a product (e.g., product 320) may be specified as an example for finding similar products that are suitable as alternatives (e.g., product 420). Accordingly, the product may have a corresponding (e.g., associated) psychometric profile (e.g., of the product itself, or its manager), which may be used in a manner similar to that described above for the psychometric profile 312 of the user 310.
As shown in FIG. 9, the method 800 may include one or more of operations 920, 960, and 970. Operation 920 is similar to operation 820 in that the access module 210 accesses a psychometric profile of a product (e.g., psychometric profile 322 of the product 320). However, in operation 920 the access module 210 accesses the psychometric profile of a first product (e.g., input product) that has been identified by a previously received submission from a user (e.g., from user 152 via the device 150). For example, the access module 210 may access (e.g., from the database 115) the psychometric profile 322 of the product 320 in response to a submission that identifies the product 320 (e.g., a request to identify other products whose associated psychometric profiles (e.g., of the products themselves, or of their managers) match the psychometric profile 322 of the product 320). The accessed psychometric profile the first product may therefore be used in operation 840 for comparison with other psychometric profiles.
Operation 960 is similar to operation 860 in that the recommender module 280 identifies a product (e.g., product 420) as a match to something. However, in operation 950, the recommender module 280 identifies a second product (e.g., output product) as a match for the first product (e.g., input product) discussed above with respect operation 920. For example, the product 420 may be identified as a product-to-product match (e.g., a product whose psychometric profile exactly, closely, or sufficiently matches the psychometric profile of the first product), a product-to-manager match (e.g., a product whose manager, group of managers, or managing entity has a psychometric profile that exactly, closely, or sufficiently matches the psychometric profile the first product), a manager-to-manager match (e.g., a product whose manager, group of managers, or managing entity has a psychometric profile that exactly, closely, or sufficiently matches the psychometric profile of the manager, group of managers, or managing entity of the first product), or any suitable combination thereof. This identification of the product 420 may be likewise performed based on (e.g., by performing) one or more of the comparisons performed in operation 840.
Operation 970 is similar to operation 870 in that the user interface module 220 causes the user interface (e.g., executing on the client device 130) to present a reference to a product. However, in operation 970, the user interface module 220 causes the user interface to present a reference to the second product (e.g., product 420, which may be an output product) identified in operation 960. This reference may be presented to a user (e.g., to the user 152 via the device 150). The user interface may form all or part of an application (e.g., a browser application) executing on the device 150, and the user interface module 220 may cause the user interface to present the reference to the second product on a display of the device 150. Moreover, the reference may be presented as a recommendation of the second product. According to various example embodiments, the reference may take the form of a search result, an advertisement, a listing, a hyperlink, a suggestion, or other notification that references the second product (e.g., by name or other identifier, such as a ticker symbol). Operation 970 may be performed in response to operation 960.
According to certain example embodiments, the recommendation machine 110 is configured to generate or update a psychometric profile for a person (e.g., psychometric profile 312 for the user 310 or psychometric profile 332 for the manager 330), for a group of persons (e.g., psychometric profile 412 for the group 410 of users, or psychometric profile 432 for the group 430 of managers), or for an entity (e.g., psychometric profile 462 for the user entity 460, or psychometric profile 482 for the managing entity 480) by generating or updating a market model (e.g., market model 710) for the person, group, or entity being modeled by the psychometric profile. A person (e.g., user 152) may be considered as a test subject in the administration of one or more tests (e.g., an IAT or a test for agreement with various metaphor statements) to obtain results that may be incorporated into his or her psychometric profile.
As shown in FIG. 10, the method 800 may include one or more of operations 1010, 1020, 1030, 1040, and 1050. In operation 1010, the user interface module 220 causes the user interface to present a metaphor statement (e.g., metaphor statement 510 or “The market is a war zone.”) to the test subject (e.g., to the user 152, via a display on the device 150) and ask that the test subject indicate his or her level of agreement with the metaphor statement. The user interface module 220 may further receive the indicated level of agreement, as a submission by the test subject (e.g., from the device 150).
In operation 1020, based on this indicated level of agreement, an influence strength of the metaphor statement presented in operation 1010 may be calculated (e.g., as influence strength 512 for the metaphor statement 510). Where the test subject is the user 310, the group 410 of users, or the user entity 460, operation 1020 may be performed by the user analysis module 230 (e.g., via the market metaphor module 232). Where the test subject is the manager 330, the group 430 of managers, or the managing entity 480, operation 1020 may be performed by the product analysis module 240 (e.g., via the market metaphor module 242). In either case, the influence strength may be a normalized value that represents a relative degree of influence that the metaphor statement holds with respect to the test subject, in comparison to other metaphor statements. For example, the influence strength may be normalized to values between zero and one, where zero represents no influence on the test subject, and one represents a maximum influence on the test subject. As shown in FIG. 10, operations 1010 at 1020 may be repeated so that several different metaphor statements are presented to the test subject and their respective influence strengths may be calculated.
In operation 1030, a psychometric profile is generated or updated for the test subject (e.g., psychometric profile 312 or 332). As shown in FIG. 10, this may be accomplished by generating or updating a market model (e.g., market model 710) for the test subject, based on the influence strength (e.g., influence strength 512) of one or more market metaphors (e.g., metaphor statement 510). This market model may then be included in the resulting psychometric profile. Where the test subject is the user 310, the group 410 of users, or the user entity 460, operation 1030 may be performed by the user analysis module 230 (e.g., via the market metaphor module 232). Where the test subject is the manager 330, the group 430 of managers, or the managing entity 480, operation 1030 may be performed by the product analysis module 240 (e.g., via the market metaphor module 242).
In situations where the psychometric profile (e.g., psychometric profile 412 or 452) models a set of multiple individual users (e.g., group 410 of users, or user entity 460), the group module 236 within the user analysis module 230 may aggregate respective market models for each of the individual users and generate or update a market model for the entire set. Similarly, where the psychometric profile (e.g., psychometric profile 432 or 482) models a set of multiple individual managers (e.g., group 430 of managers, or managing entity 480), the group module 246 within the product analysis module 240 may aggregate respective market models for each of the individual managers and generate or update a market model for the set as a whole.
In some example embodiments, the test subject may be prompted to accept, edit, or confirm the resulting psychometric profile. Accordingly, in operation 1040, the user interface module 220 may present this psychometric profile (e.g., psychometric profile 312) to the test subject (e.g., user 152, via the device 150). The user interface module 220 may further receive a response that indicates such acceptance, editing, or confirmation by the test subject (e.g., from the device 150).
In operation 1050, the user analysis module 230 stores the psychometric profile of the test subject (e.g., psychometric profile 312) in the database 115. Accordingly, the database 115 may store the psychometric profile for subsequent access by the access module 210 in performing operation 810, operation 830, or both. As shown in FIG. 10, one or more of operations 810 and 830 may then be performed as previously described above with respect to FIG. 8.
According to various example embodiments, a psychometric profile for a person, a group of persons, or an entity (e.g., psychometric profile 312 for the user 310, or psychometric profile 332 for the manager 330) may be generated or updated by generating or updating a risk model (e.g., risk model 720). This may be accomplished by presenting (e.g., administering) one or more IAT's to the test subject (e.g., a first unprimed IAT, followed by a presentation of priming content, followed by a second primed IAT).
As shown in FIG. 11, the method 800 may include one or more of operations 1110, 1118, and 1120. In operation 1110, the user interface module 220 causes the user interface to present (e.g., administer) an IAT (e.g., a first, unprimed IAT) to the test subject (e.g., to the user 152, via a display on the device 150). The user interface module 220 may further receive responses of the test subject to the presented IAT (e.g., from the device 150). Where the test subject is the user 310, the group 410 of users, or the user entity 460, the user analysis module 230 (e.g., via the implicit association module 235) may calculate one or more results (e.g., unprimed results) of the IAT from the received responses. Where the test subject is the manager 330, the group 430 of managers, or the managing entity 480, the product analysis module 240 (e.g., via the implicit association module 245) may calculate such results from the received responses.
In operation 1118, the user interface module 220 causes the user interface to present a priming scenario to the test subject (e.g., to the user 152, via the display on the device 150). Presented after a first (e.g., unprimed) IAT, the priming scenario may cause the test subject to respond differently to a second (e.g., primed) IAT. In the context of recommending financial products (e.g., hedge funds), the priming scenario may include one or more images or descriptions of financial disasters, financial crisis, or other situations likely to evoke fear or insecurity in the test subject regarding financial risk.
In operation 1120, the user interface module 220 causes the user interface to present (e.g., administer) a further IAT (e.g., a second, primed IAT) to the test subject (e.g., to the user 152, via a display on the device 150). The user interface module 220 may further receive responses of the test subject to this further IAT (e.g., from the device 150). Where the test subject is the user 310, the group 410 of users, or the user entity 460, the user analysis module 230 (e.g., via the implicit association module 235) may calculate one or more results (e.g., primed results) of this further IAT from the received responses. Where the test subject is the manager 330, the group 430 of managers, or the managing entity 480, the product analysis module 240 (e.g., via the implicit association module 245) may calculate such results from the received responses.
In example embodiments that involve presenting one or more IATs (e.g., as in operation 1110), performance of operation 1030 may include generating or updating a risk model (e.g., risk model 720) based on the results of the one or more IATs (e.g., unprimed results, primed results, or both). This risk model may then be included in the resulting psychometric profile (e.g., psychometric profile 312). Where the test subject is the user 310, the group 410 of users, or the user entity 460, operation 1030 may be performed by the user analysis module 230 (e.g., via the risk module 234). Where the test subject is the manager 330, the group 430 of managers, or the managing entity 480, operation 1030 may be performed by the product analysis module 240 (e.g., via the risk module 244).
In situations where the psychometric profile (e.g., psychometric profile 412 or 462) models a set of multiple individual users (e.g., group 410 of users, or user entity 460), the group module 236 within the user analysis module 230 may aggregate respective risk models for each of the individual users and generate or update a risk model for the entire set. Similarly, where the psychometric profile (e.g., psychometric profile 432 or 482) models a set of multiple individual managers (e.g., group 430 of managers, or managing entity 480), the group module 246 within the product analysis module 240 may aggregate respective risk models for each of the individual managers and generate or update a risk model for the set as a whole. As shown in FIG. 11, one or more of operations 1040, 1050, 810, and 830 may then be performed as previously described above with respect to FIGS. 8 and 10.
According to some example embodiments, the recommendation machine 110 is configured to generate a psychometric profile (e.g., psychometric profile 322) as an inferred psychometric profile of a product (e.g., product 320) or a quasi-psychometric profile of the product. As shown in FIG. 12, the method 800 may include one or more of operations 1210, 1220, 1230, 1240, 1250, 1260, 1270, 1280, and 1290, prior to operation 820.
In operation 1210, the access module 210 accesses the statistical data 610 (e.g., performance statistics) that indicate changes in the value of a product (e.g., product 320) within the market over time. In the context of recommending financial products (e.g., a hedge fund), the statistical data 610 may include monthly returns (e.g., monthly absolute returns for the hedge fund).
In operation 1220, the product analysis module 240 calculates a normalized representation of kurtosis for the product (e.g., product 320), based on the statistical data 610 accessed in operation 1210. This may be performed by calculating the kurtosis and normalizing it relative to other products. For example, a kurtosis score may be calculated and normalized between zero and one, where zero represents the lowest kurtosis compared to other products, and one represents the highest kurtosis compared to other products. According to some example embodiments, the normalized kurtosis score for a financial product represents a measure of relative abundance in months with unusually high returns or unusually low returns. Thus, a relatively high score (e.g., high percentile) may indicate a risk-seeking financial product, while a relatively low score (e.g., low percentile) may indicate a risk-averse financial product. As used herein, the term “kurtosis” refers to a measure of the relative population of data extrema. Positive kurtosis indicates a data distribution with “fat tails” (e.g., a higher population of extreme positive and negative data points, relative to a normal distribution), in contrast to negative kurtosis indicating a distribution with “thin tails” (e.g., a lower population of extreme positive and negative data points, relative to a normal distribution). The term “kurtosis” is intended to include the fourth-moment (4th-moment) of the normal distribution (e.g., the fourth power of the differences of each data point and the mean of the distribution).
In operation 1230, the product analysis module 240 calculates a normalized representation of skewness for the product (e.g., product 320), based on the statistical data 610 accessed in operation 1210. This may be performed by calculating the skewness and normalizing it relative to other products. For example, a skew score may be calculated and normalized between zero and one, where zero represents the lowest skew compared to other products, and one represents the highest skew compared to other products. According to some example embodiments, the normalized skewness score for a financial product represents a measure of relative asymmetry in monthly returns (e.g., a frequency of monthly losses compared to a frequency of monthly gains). Thus, a relatively high score may indicate an agile financial product that is able to react quickly to adverse conditions and thereby limit losses, while a relatively low score may indicate the opposite. As used herein, the term “skewness” refers to a measure of the relative population of positive or negative data. Positive skew indicates a data distribution with more positive data than negative data, especially in the “tails” of the distribution, in contrast to negative skew indicating a distribution with a “negative tail,” and relatively fewer positive data points. The term “skewness” is intended to include the third-moment (3rd-moment) of the normal distribution (e.g., the third power of the differences of each data point and the mean of the distribution).
In operation 1240, the product analysis module 240 calculates a standard deviation of a set of rolling standard deviations, based on the statistical data 610 accessed in operation 1210, and normalizes this calculated standard deviation relative to other products. This may be performed by calculating the standard deviation of monthly returns within each of multiple overlapping 12-month spans of time represented in the statistical data 610. These are the rolling standard deviations. A further standard deviation may be calculated from these rolling standard deviations, which may be considered as the standard deviation of the set of rolling standard deviations. This may result in a score that represents the degree to which the value of the product (e.g., product 320) is stationary over time. After normalization relative to other products, the score represents a degree of relative “stationarity” of the product in relation to other products. For example, the score may be normalized between zero and one, where zero represents the lowest degree of stationarity, and one represents the highest degree of stationarity compared to other products. According to some example embodiments, the normalized stationarity score for a financial product represents a measure of how well the financial product is able to control volatility in monthly returns. Thus, a relatively high score may indicate less ability to control volatility, while a relatively low score may indicate greater ability, compared to other financial products.
In operation 1250, the product analysis module 240 calculates a normalized number of products managed by a manager (e.g., manager 330) of the product (e.g., product 320). This may be performed by identifying the manager from the statistical data 610 and accessing (e.g., from news or a look up table, which may be stored in the database 115) the number of products managed by that manager. This number may be normalized relative to other products. For example, the normalized number may range between zero and one, where zero indicates that the manager manages no additional products, and one indicates that the manager manages the maximum number of additional products compared to managers of the other products.
In operation 1260, the product analysis module 240 calculates a normalized number of assets under management by a manager (e.g., manager 330) of the product (e.g., product 320). This may be performed by identifying the manager from the statistical data 610 and accessing (e.g., from news or a look up table, which may be stored in the database 115) the number of assets within products that are managed by that manager. This number may be normalized relative to other products. For example, the normalized number may range between zero and one, where zero indicates that the manager manages the lowest number of assets, and one indicates that the manager manages the maximum number of assets compared to managers of the other products.
In operation 1270, the product analysis module 240 calculates a normalized correlation of monthly returns for the product (e.g., as represented in the statistical data 610) relative to a published market indicator (e.g., the Standard & Poor's 500 index). This may be performed by accessing the monthly returns from the statistical data 610, calculating their correlation to the published market indicator, and then normalizing the correlation relative to other products. For example, the normalized correlation may range between zero and one, where zero represents the lowest correlation with the published market indicator, and one represents the highest correlation with the published market indicator, relative to other products.
In operation 1280, the product analysis module 240 creates or updates a psychometric profile for the product (e.g., psychometric profile 322 for the product 320). This may be accomplished by creating or updating an inferred or approximated market model (e.g., market model 710) for the product, creating or updating an inferred or approximated risk model (e.g., risk model 720) for the product, or both. The market model, the risk model, or both may be created or updated based on the results of one or more of operations 1220, 1230, 1240, 1250, 1260, and 1270 (e.g., the normalized kurtosis score, the normalized skewness score, the standard deviation of the rolling standard deviations, the normalized number of products managed by the manager of the product, the normalized number of assets under management by the manager, and the normalized correlation of monthly returns relative to the market indicator).
The product analysis module 240 may then include (e.g., incorporate) the market model, the risk model, or both in the psychometric profile (e.g., quasi-psychometric profile) for the product (e.g., psychometric profile 322 for the product 320). In operation 1290, the product analysis module 240 stores the generated psychometric profile for the product in the database 115. Accordingly, the database 115 may store this psychometric profile for subsequent access by the access module 210 in performing operation 820 or operation 920. As shown in FIG. 12, operation 820 may then be performed as previously described above with respect to FIG. 8. Similarly, operation 920 may then be performed as previously described above with respect to FIG. 9.
According to certain example embodiments, the recommendation machine 110 may provide a recommendation of a product (e.g., as described above with respect to operation 870 and operation 970) in response to a request submitted by a user (e.g., user 132, via the device 130). Examples are illustrated with respect to FIG. 13-15.
As shown in FIG. 13, the method 800 may include one or more of operations 1310, 1340, 1342, 1344, and 1346. In operation 1310, the user interface module 220 receives a search (e.g., search request) submitted by the user 132 from the device 130. The submitted search may include or otherwise indicate various criteria for identifying one or more products (e.g., product 320) available for recommendation. Performance of one or more of operations 810, 820, 830, and 840 may obtain (e.g., identify) a set of products (e.g., products 320, 420, and 470) that fit the psychometric profile (e.g., psychometric profile 312) of the user 132 and that fit these various search criteria specified in the submitted search. For filtering the set of products, the user interface module 220 may cause the user interface to present one or more parameter selection sliders (e.g., interactive parameter selection bars) configured to specify various filtering criteria. Example embodiments of such parameter selection sliders are illustrated and discussed with respect to FIG. 16. In certain example embodiments, such parameter sliders are used to specify the search criteria, the filtering criteria, or both.
FIG. 16 is a screenshot illustrating a user interface 1600 with parameter selection sliders, according to some example embodiments. As shown, the user interface 1600 may include a hard-edge slider 1610, a soft-edge slider 1620, the goal slider 1630, or any suitable combination thereof. The hard-edge slider 1610 includes a parameter selection bar 1612 that ranges from a minimum value (e.g., 0%) to a maximum value (e.g., 100%). The parameter selection bar 1612 may include two slidable markers (e.g., a minimum slider and a maximum slider) that are movable along the length of the parameter selection bar 1612 to specify a sub-range between the minimum and maximum values (e.g., a sub-range from 27% to 58%). As implemented in some example embodiments, this specified sub-range is absolute (e.g., “hard-edged”); all values within the sub-range are selected (e.g., as search criteria or filtering criteria), and all values beyond the sub-range are omitted (e.g., from the search criteria or filtering criteria).
The soft-edge slider 1620 includes a value bar 1622 that may similarly range from a minimum value (e.g., 0%) to a maximum value (e.g., 3%). A parameter selection bar 1622 is shown as including two slidable markers (e.g., a minimum slider and a maximum slider) that are movable along the length of the parameter selection bar 1622 to specify a sub-range between a minimum and maximum values (e.g., a sub-range from 0.5% to 1.5%). As implemented in some example embodiments, this specified sub-range is not absolute (e.g., not “hard-edged”), and while all values within sub-range are selected (e.g., as search criteria or filtering criteria), some additional values beyond the sub-range are also allowed to be selected (e.g., as part of the same search criteria or same filtering criteria). The selection of such additional values may be governed by an importance bar 1624 and its slidable marker (e.g., an importance slider) that is movable on the importance bar 1624 to specify an importance value (e.g., an importance score of 7 on a scale of 1 to 10). The importance value may specify a margin for additional values, such that additional values that fall outside the sub-range by less than the margin are included in the selection. For example, a high importance value may cause a selection to be more strict (e.g., thin margin) and allow inclusion of fewer additional values outside the sub-range, while a low importance value may cause a selection to be less strict (e.g., fat margin) and allow inclusion of more additional values outside the sub-range. In certain example embodiments, the influence strength 512 for the metaphor statement 510 is specified (e.g., in operation 1010) by a test subject operating a slidable marker of an importance bar, similar to the importance bar 1624, presented contemporaneously with the metaphor statement 510.
The goal slider 1630 includes a parameter selection bar 1632 that may likewise range from a minimum value (e.g., 0 years) to a maximum value (e.g., 30 years). A parameter selection bar 1632 is shown as including a single slidable marker (e.g., a value slider) that is movable along the length of the parameter selection bar 1632 to specify a goal value (e.g., an ideal value or a desired value) within the total range between the minimum and maximum values. As implemented in some example embodiments, this specified goal value is not absolute, and while the goal value is selected (e.g., as a search criterion or a filtering criterion), some additional values above and below the goal value are also allowed to be selected (e.g., as additional search criteria or additional filtering criteria). The selection of such additional values may be governed by an importance bar 1634 and its slidable marker (e.g., an importance slider) that is movable on the importance bar 1634 to specify an importance value (e.g., an importance score of 8 on a scale of 1 to 10). The importance value may specify a margin for additional values, such that additional values that fall outside the sub-range by less than the margin are included in the selection. For example, a high importance value may cause a selection to be more strict (e.g., narrow or small margin) and allow inclusion of fewer additional values that differ from the goal value (e.g., only those additional values that are very close to the goal value), while a low importance value may cause a selection to be less strict (e.g., wide or big margin) and allow inclusion of more additional values that differ from the goal value (e.g., values further above or below the goal value).
Returning the FIG. 13, in operation 1340, the user interface module 220 causes the user interface 1600 to present one or more parameter selection sliders for specifying various filtering criteria that may be applied to results of the search (e.g., search request) received in operation 1310. For example, the user interface module 220 may cause a user interface 1600 to present the hard-edge slider 1610, the soft-edge slider 1620, the goal slider 1630, or any suitable combination thereof
In operation 1342, the user interface module 220 receives a selection of a range specified by the hard-edge slider 1610 (e.g., as specified by the user 132 via the device 130). In operation 1344, the user interface module 220 receives a selection of a range specified by the soft-edge slider 1620, along with a corresponding importance value (e.g., as specified by the user 132 via the device 130). In operation 1346, the user interface module 220 receives a selection of a goal value specified by the goal slider 1630, along with a corresponding importance value (e.g., as specified by the user 132 via the device 130). Although operations 1342, 1344, and 1346 have been described in the context of receiving filtering criteria, similar operations may be performed to receive the search criteria discussed above with respect to operation 1310.
FIG. 13 additionally shows one or more of operations 810, 820, 830, 840, 850, and 870 being performed (e.g., as described above with respect to FIG. 8). Based on filtering criteria obtained from one or more of operations 1342, 1344, and 1346, as well as the psychometric profile (e.g., psychometric profile 312) of the user 132, operation 850 may be performed to identify a product (e.g., product 320) that matches the search criteria for operation 1310, as well as the filtering criteria. Thus, the identification of the product may be in response to the search (e.g., search request) submitted by the user 132 and received in operation 1310.
As shown in FIG. 14, the method 800 may include operation 1410. In operation 1410, the user interface module 220 receives a request (e.g., match request) to identify one or more products that match the user 132. Such a request may be submitted by the user 132 from the device 130. The submitted request may include or otherwise indicate various additional criteria for identifying one or more matching products (e.g., product 320). Performance of one or more of operations 810, 820, 830, and 840 may obtain (e.g., identify) a set of products that fit the psychometric profile of the user 132 and may also fit any additional criteria specified in the request. For filtering the set of products, the user interface module 220 may cause the user interface to present one or more parameter selection sliders to specify filtering criteria, as discussed above with respect to FIG. 16. In certain example embodiments, such parameter sliders are used to specify the additional criteria, the filtering criteria, or both.
FIG. 14 also shows one or more of operations 810, 820, 830, 840, 860, 870, 1340, 1342, 1344, and 1346 being performed (e.g., as described above with respect to FIGS. 8 and 13). Based on filtering criteria obtained from one or more of operations 1342, 1344, and 1346, as well as the psychometric profile (e.g., psychometric profile 312) of the user 132, operation 860 may be performed to identify a product (e.g., product 320) that matches the user 132, in addition to fulfilling the filtering criteria. Thus, the identification of the product may be in response to the request (e.g., match request) submitted by the user 132 and received in operation 1410.
As shown in FIG. 15, the method 800 may include operation 1510. In operation 1510, the user interface module 220 receives a request (e.g., alternative request) to identify one or more second products (e.g., output products, such as products 420 and 470) as alternatives to a first product (e.g., input product, such as product 320). Such a request may be submitted by the user 132 from the device 130. The submitted request may include or otherwise indicate various additional criteria for identifying suitable alternative products.
FIG. 15 also shows one or more of operations 1340, 1342, 1344, 1346, 810, 920, 830, 840, 950, and 970 being performed (e.g., as described above with respect to FIGS. 8, 9, and 13). Based on filtering criteria obtained from one or more of operations 1342, 1344, and 1346, as well as the psychometric profile (e.g., psychometric profile 322) of the first product (e.g., product 320), operation 960 may be performed to identify a second product (e.g., product 420) that fulfills the filtering criteria and is sufficiently similar to the first product to be recommended as an alternative to the first product. In some example embodiments, the identified second product may also have a psychometric profile that matches the psychometric profile of the user 132. Thus, the identification of the product may be in response to the request (e.g., alternative request) submitted by the user 132 and received in operation 1510.
According to various example embodiments, one or more of the methodologies described herein may facilitate assessments of implicit and non-conscious (e.g., unconscious) psychological understandings of financial markets, as held by financial decision-makers. Moreover, one or more of the methodologies described herein may facilitate determinations of non-conscious propensities for risk-taking or safety-seeking in financial decision-makers, as well as determinations of the influence of situational factors (e.g., market volatility, market crisis, or change market conditions) on such non-conscious propensities. Hence, one or more of the methodologies described herein may facilitate making recommendations of financial products by matching financial decision-makers (e.g., hedge fund investors) to investments (e.g., hedge funds), enabling prospective investors to search and identify investments using psychometric profiles, identifying investment alternatives based on psychometric profiles (e.g., including quasi-psychometric profiles of such alternatives), or any suitable combination thereof.
When these effects are considered in aggregate, one or more of the methodologies described herein may obviate a need for certain efforts or resources that otherwise would be involved in making recommendations of financial products. Efforts expended by a user in identifying obtaining such recommendations may be reduced by one or more of the methodologies described herein. Computing resources used by one or more machines, databases, or devices (e.g., within the network environment 100) may similarly be reduced. Examples of such computing resources include processor cycles, network traffic, memory usage, data storage capacity, power consumption, and cooling capacity.
Although various example embodiments are discussed above with respect to recommendation of one or more financial products (e.g., hedge funds, mutual funds, exchange-traded funds, stocks, stock options, bonds, commodities, certificates of deposit, and other investment instruments), the systems and methods discussed herein may be applied to other types of products or any suitable combination of products (e.g., goods, services, information, and licenses). For example, the systems and methods discussed herein may facilitate recommendation of real estate (e.g., a house, an apartment, a vacation rental, a neighborhood, a community, a city, a state, or a country), personnel (e.g., services of a prospective employee, consultant, vendor, supplier, customer, manager, or team thereof), goods (e.g., a car, a computer, or a digital camera), recreation (e.g., an offer for leisure activity, a club membership, a vacation, a cruise, or a holiday package), web-based services (e.g., a messaging service, a data storage service, or a social networking service), healthcare services (e.g., of a physician, a clinic, a hospital, or a patient thereof), mental health services (e.g., of a psychotherapist or a client thereof), educational services (e.g., of a school, a college, university, a teacher, a professor, a seminar, a training camp, or a student thereof), hospitality services (e.g., of a hotel, a bed-and-breakfast, a guesthouse, a hostel, a campground, or a cruise line), or any suitable combination thereof. In addition to products available for sale, the systems and methods discussed herein may facilitate recommendation of any selectable thing that may be associated with (e.g., assigned or mapped to) a psychometric profile (e.g., a vocation, a religion, or a hobby).
FIG. 17 is a block diagram illustrating components of a machine 1700, according to some example embodiments, able to read instructions 1124 from a machine-readable medium 1722 (e.g., a machine-readable storage medium, a computer-readable storage medium, or any suitable combination thereof) and perform any one or more of the methodologies discussed herein, in whole or in part. Specifically, FIG. 17 shows the machine 1700 in the example form of a computer system within which the instructions 1724 (e.g., software, a program, an application, an applet, an app, or other executable code) for causing the machine 1700 to perform any one or more of the methodologies discussed herein may be executed, in whole or in part. In alternative embodiments, the machine 1700 operates as a standalone device or may be connected (e.g., networked) to other machines. In a networked deployment, the machine 1700 may operate in the capacity of a server machine or a client machine in a server-client network environment, or as a peer machine in a distributed (e.g., peer-to-peer) network environment. The machine 1700 may be a server computer, a client computer, a personal computer (PC), a tablet computer, a laptop computer, a netbook, a cellular telephone, a smartphone, a set-top box (STB), a personal digital assistant (PDA), a web appliance, a network router, a network switch, a network bridge, or any machine capable of executing the instructions 1724, sequentially or otherwise, that specify actions to be taken by that machine. Further, while only a single machine is illustrated, the term “machine” shall also be taken to include any collection of machines that individually or jointly execute the instructions 1724 to perform all or part of any one or more of the methodologies discussed herein.
The machine 1700 includes a processor 1702 (e.g., a central processing unit (CPU), a graphics processing unit (GPU), a digital signal processor (DSP), an application specific integrated circuit (ASIC), a radio-frequency integrated circuit (RFIC), or any suitable combination thereof), a main memory 1704, and a static memory 1706, which are configured to communicate with each other via a bus 1708. The processor 1702 may contain microcircuits that are configurable, temporarily or permanently, by some or all of the instructions 1724 such that the processor 1702 is configurable to perform any one or more of the methodologies described herein, in whole or in part. For example, a set of one or more microcircuits of the processor 1702 may be configurable to execute one or more modules (e.g., software modules) described herein.
The machine 1700 may further include a graphics display 1710 (e.g., a plasma display panel (PDP), a light emitting diode (LED) display, a liquid crystal display (LCD), a projector, a cathode ray tube (CRT), or any other display capable of displaying graphics or video). The machine 1700 may also include an alphanumeric input device 1712 (e.g., a keyboard or keypad), a cursor control device 1714 (e.g., a mouse, a touchpad, a trackball, a joystick, a motion sensor, an eye tracking device, or other pointing instrument), a storage unit 1716, an audio generation device 1718 (e.g., a sound card, an amplifier, a speaker, a headphone jack, or any suitable combination thereof), and a network interface device 1720.
The storage unit 1716 includes the machine-readable medium 1722 (e.g., a tangible and non-transitory machine-readable storage medium) on which are stored the instructions 1724 embodying any one or more of the methodologies or functions described herein. The instructions 1724 may also reside, completely or at least partially, within the main memory 1704, within the processor 1702 (e.g., within the processor's cache memory), or both, before or during execution thereof by the machine 1700. Accordingly, the main memory 1704 and the processor 1702 may be considered machine-readable media (e.g., tangible and non-transitory machine-readable media). The instructions 1724 may be transmitted or received over the network 190 via the network interface device 1720. For example, the network interface device 1720 may communicate the instructions 1724 using any one or more transfer protocols (e.g., hypertext transfer protocol (HTTP)).
In some example embodiments, the machine 1700 may be a portable computing device, such as a smart phone or tablet computer, and have one or more additional input components 1730 (e.g., sensors or gauges). Examples of such input components 1730 include an image input component (e.g., one or more cameras), an audio input component (e.g., a microphone), a direction input component (e.g., a compass), a location input component (e.g., a global positioning system (GPS) receiver), an orientation component (e.g., a gyroscope), a motion detection component (e.g., one or more accelerometers), an altitude detection component (e.g., an altimeter), and a gas detection component (e.g., a gas sensor). Inputs harvested by any one or more of these input components may be accessible and available for use by any of modules described herein.
As used herein, the term “memory” refers to a machine-readable medium able to store data temporarily or permanently and may be taken to include, but not be limited to, random-access memory (RAM), read-only memory (ROM), buffer memory, flash memory, and cache memory. While the machine-readable medium 1722 is shown in an example embodiment to be a single medium, the term “machine-readable medium” should be taken to include a single medium or multiple media (e.g., a centralized or distributed database, or associated caches and servers) able to store instructions. The term “machine-readable medium” shall also be taken to include any medium, or combination of multiple media, that is capable of storing the instructions 1724 for execution by the machine 1700, such that the instructions 1724, when executed by one or more processors of the machine 1700 (e.g., processor 1702), cause the machine 1700 to perform any one or more of the methodologies described herein, in whole or in part. Accordingly, a “machine-readable medium” refers to a single storage apparatus or device, as well as cloud-based storage systems or storage networks that include multiple storage apparatus or devices. The term “machine-readable medium” shall accordingly be taken to include, but not be limited to, one or more tangible data repositories in the form of a solid-state memory, an optical medium, a magnetic medium, or any suitable combination thereof
Throughout this specification, plural instances may implement components, operations, or structures described as a single instance. Although individual operations of one or more methods are illustrated and described as separate operations, one or more of the individual operations may be performed concurrently, and nothing requires that the operations be performed in the order illustrated. Structures and functionality presented as separate components in example configurations may be implemented as a combined structure or component. Similarly, structures and functionality presented as a single component may be implemented as separate components. These and other variations, modifications, additions, and improvements fall within the scope of the subject matter herein.
Certain embodiments are described herein as including logic or a number of components, modules, or mechanisms. Modules may constitute either software modules (e.g., code embodied on a machine-readable medium or in a transmission signal) or hardware modules. A “hardware module” is a tangible unit capable of performing certain operations and may be configured or arranged in a certain physical manner. In various example embodiments, one or more computer systems (e.g., a standalone computer system, a client computer system, or a server computer system) or one or more hardware modules of a computer system (e.g., a processor or a group of processors) may be configured by software (e.g., an application or application portion) as a hardware module that operates to perform certain operations as described herein.
In some embodiments, a hardware module may be implemented mechanically, electronically, or any suitable combination thereof. For example, a hardware module may include dedicated circuitry or logic that is permanently configured to perform certain operations. For example, a hardware module may be a special-purpose processor, such as a field programmable gate array (FPGA) or an ASIC. A hardware module may also include programmable logic or circuitry that is temporarily configured by software to perform certain operations. For example, a hardware module may include software encompassed within a general-purpose processor or other programmable processor. It will be appreciated that the decision to implement a hardware module mechanically, in dedicated and permanently configured circuitry, or in temporarily configured circuitry (e.g., configured by software) may be driven by cost and time considerations.
Accordingly, the phrase “hardware module” should be understood to encompass a tangible entity, be that an entity that is physically constructed, permanently configured (e.g., hardwired), or temporarily configured (e.g., programmed) to operate in a certain manner or to perform certain operations described herein. As used herein, “hardware-implemented module” refers to a hardware module. Considering embodiments in which hardware modules are temporarily configured (e.g., programmed), each of the hardware modules need not be configured or instantiated at any one instance in time. For example, where a hardware module comprises a general-purpose processor configured by software to become a special-purpose processor, the general-purpose processor may be configured as respectively different special-purpose processors (e.g., comprising different hardware modules) at different times. Software may accordingly configure a processor, for example, to constitute a particular hardware module at one instance of time and to constitute a different hardware module at a different instance of time.
Hardware modules can provide information to, and receive information from, other hardware modules. Accordingly, the described hardware modules may be regarded as being communicatively coupled. Where multiple hardware modules exist contemporaneously, communications may be achieved through signal transmission (e.g., over appropriate circuits and buses) between or among two or more of the hardware modules. In embodiments in which multiple hardware modules are configured or instantiated at different times, communications between such hardware modules may be achieved, for example, through the storage and retrieval of information in memory structures to which the multiple hardware modules have access. For example, one hardware module may perform an operation and store the output of that operation in a memory device to which it is communicatively coupled. A further hardware module may then, at a later time, access the memory device to retrieve and process the stored output. Hardware modules may also initiate communications with input or output devices, and can operate on a resource (e.g., a collection of information).
The various operations of example methods described herein may be performed, at least partially, by one or more processors that are temporarily configured (e.g., by software) or permanently configured to perform the relevant operations. Whether temporarily or permanently configured, such processors may constitute processor-implemented modules that operate to perform one or more operations or functions described herein. As used herein, “processor-implemented module” refers to a hardware module implemented using one or more processors.
Similarly, the methods described herein may be at least partially processor-implemented, a processor being an example of hardware. For example, at least some of the operations of a method may be performed by one or more processors or processor-implemented modules. Moreover, the one or more processors may also operate to support performance of the relevant operations in a “cloud computing” environment or as a “software as a service” (SaaS). For example, at least some of the operations may be performed by a group of computers (as examples of machines including processors), with these operations being accessible via a network (e.g., the Internet) and via one or more appropriate interfaces (e.g., an application program interface (API)).
The performance of certain operations may be distributed among the one or more processors, not only residing within a single machine, but deployed across a number of machines. In some example embodiments, the one or more processors or processor-implemented modules may be located in a single geographic location (e.g., within a home environment, an office environment, or a server farm). In other example embodiments, the one or more processors or processor-implemented modules may be distributed across a number of geographic locations.
Some portions of the subject matter discussed herein may be presented in terms of algorithms or symbolic representations of operations on data stored as bits or binary digital signals within a machine memory (e.g., a computer memory). Such algorithms or symbolic representations are examples of techniques used by those of ordinary skill in the data processing arts to convey the substance of their work to others skilled in the art. As used herein, an “algorithm” is a self-consistent sequence of operations or similar processing leading to a desired result. In this context, algorithms and operations involve physical manipulation of physical quantities. Typically, but not necessarily, such quantities may take the form of electrical, magnetic, or optical signals capable of being stored, accessed, transferred, combined, compared, or otherwise manipulated by a machine. It is convenient at times, principally for reasons of common usage, to refer to such signals using words such as “data,” “content,” “bits,” “values,” “elements,” “symbols,” “characters,” “terms,” “numbers,” “numerals,” or the like. These words, however, are merely convenient labels and are to be associated with appropriate physical quantities.
Unless specifically stated otherwise, discussions herein using words such as “processing,” “computing,” “calculating,” “determining,” “presenting,” “displaying,” or the like may refer to actions or processes of a machine (e.g., a computer) that manipulates or transforms data represented as physical (e.g., electronic, magnetic, or optical) quantities within one or more memories (e.g., volatile memory, non-volatile memory, or any suitable combination thereof), registers, or other machine components that receive, store, transmit, or display information. Furthermore, unless specifically stated otherwise, the terms “a” or “an” are herein used, as is common in patent documents, to include one or more than one instance. Finally, as used herein, the conjunction “or” refers to a non-exclusive “or,” unless specifically stated otherwise.

Claims

What is claimed is:

1. A method comprising:

accessing a first psychometric profile of a user,

the first psychometric profile including a market model of the user and a risk model of the user,

the market model of the user indicating an unconscious characterization applied by the user to a market for products,

the risk model of the user indicating an unconscious degree of risk tolerable by the user;

accessing a plurality of psychometric profiles of products within the market,

a second psychometric profile among the plurality of psychometric profiles being correlated with a product within the market to which the unconscious characterization is applied;

using a processor, identifying the product based on a comparison of the first psychometric profile of the user to the second psychometric profile correlated to the product; and

causing a user interface to present the user with a reference to the product in response to the identifying of the product based on the comparison of the first and second psychometric profiles.

2. The method of claim 1 further comprising:

generating the first psychometric profile of the user,

the generating of the first psychometric profile including generating the market model of the user based on a metaphor statement presented to the user and an indicated level of agreement by the user with the metaphor statement,

the metaphor statement being a figurative description of the market.

3. The method of claim 2 further comprising:

causing the user interface to present the metaphor statement on a device of the user; and

receiving the indicated level of agreement by the user with the presented metaphor statement that figuratively describes the market.

4. The method of claim 1 further comprising:

generating the first psychometric profile of the user,

the generating of the first psychometric profile including generating the risk model of the user based on a result of an implicit association test completed by the user,

the result indicating the unconscious degree of risk tolerable by the user.

5. The method of claim 4 further comprising:

administering the implicit association test by causing the user interface to present the implicit association test on a device of the user and receive responses of the user to the implicit association test; and

calculating the result from the received responses of the user to the administered implicit association test.

6. The method of claim 4, wherein:

the result of the implicit association test is an unprimed result of an unprimed implicit association test administered to the user;

the generating of the risk model is based on a primed result of a primed implicit association test administered to the user after the unprimed implicit association test; and the method further comprises

administering the unprimed implicit association test on a device of the user and subsequently administering the primed implicit association test on the device of the user, the unprimed and primed implicit association tests being administered by the causing the user interface to present the

unprimed and primed implicit association tests on the device of the user.

7. The method of claim 6 further comprising:

causing the user interface to present priming content to the user between the unprimed and primed implicit association tests; and wherein

the calculating of the result is based on unprimed responses of the user to the unprimed implicit association test and based on primed responses of the user to the primed implicit association test.

8. The method of claim 7, wherein:

the result indicates the unconscious degree of risk tolerable by the user in regard to financial risk; and

the priming content includes a description of a financial disaster scenario.

9. The method of claim 1 further comprising:

generating the second psychometric profile correlated with the product,

the generating of the second psychometric profile including generating a further market model of a manager that manages the product,

the further market model indicating an unconscious characterization applied by the manager to the market,

the further market model being generated based on a metaphor statement presented to the manager and an indicated level of agreement by the manager with the metaphor statement,

the metaphor statement being a figurative description of the market.

10. The method of claim 1, wherein:

generating the second psychometric profile correlated with the product,

the generating of the second psychometric profile including generating a further risk model of a manager that manages the product,

the further risk model indicating a further unconscious degree of risk tolerable by the manager,

the further risk model being generated based on a result of an implicit association test completed by the manager,

the result indicating the further unconscious degree of risk tolerable by the manager.

11. The method of claim 10 further comprising:

administering the implicit association test by causing the user interface to present the implicit association test on a device of the manager and receive responses of the manager to the implicit association test; and

calculating the result from the received responses of the manager to the administered implicit association test.

12. The method of claim 11, wherein:

the result of the implicit association test is an unprimed result of an unprimed implicit association test administered to the manager;

the generating of the risk model is based on a primed result of a primed implicit association test administered to the manager after the unprimed implicit association test; and the method further comprises

administering the unprimed implicit association test on a device of the manager and subsequently administering the primed implicit association test on the device of the manager,

the unprimed and primed implicit association tests being administered by the causing the user interface to present the unprimed and primed implicit association tests on the device of the manager.

13. The method of claim 1 further comprising:

causing the user interface to present a parameter selection bar with a minimum slider and a maximum slider, the minimum slider being operable to specify a minimum value of a range for a parameter of the product, the maximum slider being operable to specify a maximum value of the range for the parameter of the product,

the parameter selection bar being presented with a corresponding importance bar with an importance slider operable to specify an importance of the range; and

detecting specification of range and the importance of the range; and wherein

the identifying of the product includes determining that the parameter of the product falls outside of the range by a margin but that the product is nonetheless eligible for identification based on the margin and the importance of the range.

14. The method of claim 1 further comprising:

generating the second psychometric profile correlated with the product based on performance statistics indicative of changes in value of the product.

15. The method of claim 1, wherein:

the user is at least one of a first person, a first team, or a first organization; and

the second psychometric profile describes a manager that is at least one of a second person that manages the product, a second team that manages the product, or a second organization that manages the product.

16. The method of claim 1, wherein:

the product is an investment fund;

the user is a potential investor in the investment fund; and

the second psychometric profile describes a manager that manages the investment fund.

17. A non-transitory machine-readable storage medium comprising instructions that, when executed by one or more processors of a machine, cause the machine to perform operations comprising:

accessing a first psychometric profile of a user,

accessing a plurality of psychometric profiles of products within the market,

identifying the product based on a comparison of the first psychometric profile of the user to the second psychometric profile correlated to the product; and

18. The non-transitory machine-readable storage medium of claim 17, wherein the operations further comprise:

generating the first psychometric profile of the user,

the metaphor statement being a figurative description of the market.

19. A system comprising:

an access module configured to:

access a first psychometric profile of a user, the first psychometric profile including a market model of the user and a risk model of the user, the market model of the user indicating an unconscious characterization applied by the user to a market for products, the risk model of the user indicating an unconscious degree of risk tolerable by the user;

access a plurality of psychometric profiles of products within the market, a second psychometric profile among the plurality of psychometric profiles being correlated with a product within the market to which the unconscious characterization is applied;

a processor configured by a recommender module to identify the product based on a comparison of the first psychometric profile of the user to the second psychometric profile correlated to the product; and

a user interface module configured to cause a user interface to present the user with a reference to the product in response to the identifying of the product based on the comparison of the first and second psychometric profiles.

20. The system of claim 19 further comprising:

a user analysis module configured to generate the first psychometric profile of the user,

the result indicating the unconscious degree of risk tolerable by the user.