WO2023275879A1

WO2023275879A1 - Method and system for managing inventory

Info

Publication number: WO2023275879A1
Application number: PCT/IN2021/050638
Authority: WO
Inventors: Marie Nestor Damian Mariyasagayam; Sharath Kumar K.P.; Yuichi Nonaka
Original assignee: Hitachi, Ltd.
Priority date: 2021-06-30
Filing date: 2021-06-30
Publication date: 2023-01-05

Abstract

Disclosed herein is a method managing inventory. The method includes obtaining a forecast model for generating a demand forecast of stock m the inventory. In an embodiment, the forecast model is derived based on one or more planned events, using one or more supply chain data sources. Further, the method includes receiving data from one or more data sources that are external to the supply chain, at regular time intervals. Furthermore, the method includes detecting one or more unplanned events based on the data from the one or more data sources. Thereafter, the method includes generating an updated demand forecast of the stock in the inventory. The updated demand forecast helps optimize the inventory and manage the supply chain effectively.

Description

TITLE: METHOD AND SYSTEM FOR MANAGING INVENTORY

TECHNICAL FIELD

[001] The present disclosure relates to the field of inventory management. Particularly, but not exclusively, the present disclosure relates to a and system for managing inventory in a warehouse.

BACKGROUND

[002] A retail business typically needs to stock itemsin a warehouse or store in order to sell the items. Storing too few items can be undesirable because as customer demand cannot be met if the items are sold out. Stocking the items consumes time and leads to loss of customers if the items are not available on time, in turn creating loss in the retail business. Storing too many of the items also can be undesirable because the amount of space in a warehouse or store is finite and storing too many items that does not sell takes away space from items that do sell. Also, warehouse charges has to be paid for stocking the excess items. Therefore, forecast models that can accurately forecast customer demand and the inventory' sales of items are used to balance the inventory stock.

[003] Existing forecast models forecast the customer demand using merchant data, warehouse data, sales data and logistics data. The customer demand and sales are largely although not wholly dependent on the above factors. However, in the existing forecast models there is always a risk of having forecast error, which leads to excess inventory or insufficient inventory depending on overestimation or underestimation of expected demand in the future. The high forecast error value is caused as the existing systems do not consider uncertain scenarios which have big impact on the inventory stock.

[004] Therefore, there is a need to minimize the forecast error value by considering impact of all kinds of scenarios on the inventory stock. Such a solution balances the excess inventory and the insufficient inventory .

[005] The information disclosed in this background of the disclosure section is only for enhancement of understanding of the general background of the invention and should not he taken as an acknowledgment or any form of suggestion that this information forms the prior art already known to a person skilled in the art.

SUMMARY

[006] Additional features and advantages are realized through the techniques of the present disclosure. Other embodiments and aspects of the disclosure are described in detail herein and are considered a part of the claimed disclosure.

[007] Disclosed herein is a method managing stock in an inventory. The method includes obtaining a forecast model for generating a demand forecast of stock in the inventory. In an embodiment, the forecast model is derived based on one or more planned events, using one or more supply chain data sources. Further, the method includes receiving data from one or more data sources that are external to the supply chain, at regular time intervals. Furthermore, the method includes detecting one or more unplanned events based on the data from the one or more data sources. Thereafter, the method includes generating an updated demand forecast of the stock in the inventory.

[008] In an embodiment, a system for managing stock in an inventory. The system includes a memory and one or more processors. The one or more processors are configured for obtaining a forecast model for generating a demand forecast of stock in the inventory. The forecast model is derived based on one or more planned events, using one or more supply chain data sources. Further, the one or more processors are configured for receiving data from one or more data, sources that are external to the supply chain, at regular time intervals. Furthermore, one or more processors are configured for detecting one or more unplanned events based on the data from the one or more data sources. Thereafter, the one or more processors are configured for generating an updated demand forecast of the stock in the inventory.

[009] The foregoing summary is illustrative only and is not intended to be in any way limiting. In addition to the illustrative aspects, embodiments, and features described above, further aspects, embodiments, and features may become apparent by reference to the drawings and the following detailed description. BRIEF DESCRIPTION OF THE ACCOMPANYING DRAWINGS

[0010] The novel features and characteristics of the disclosure are set forth in the appended claims. The disclosure itself, however, as well as a preferred mode of use, further objectives and advantages thereof, may best be understood by reference to the following detailed description of an illustrative embodiment when read in conjunction with the accompanying drawings. The accompanying drawings, which are incorporated in and constitute a part of this disclosure, illustrate exemplary embodiments and, together with the description, serve to explain the disclosed principles. In the figures, the left-most digit(s) of a reference number identifies the figure in winch the reference number first appears. One or more embodiments are now^r described, by way of example only, with reference to the accompanying figures wherein like reference numerals represent like elements and in which:

[0011] Fig. 1 shows an exemplary environment for managing stock in an inventory, in accordance with some embodiments of the present disclosure;

[0012] Fig. 2 shows a detailed block diagram of an inventory management system for managing stock in an inventory, in accordance with some embodiments of the present disclosure;

[0013] Fig. 3 shows a flowchart illustrating a method for generating demand forecast using micro and macro data, in accordance with some embodiment of the present disclosure;

[0014] Fig, 4 shows a flowchart illustrating a method for generating demand forecast using macro data, in accordance with some embodiment of the present disclosure;

[0015] Fig. 5 show¾ a flowchart illustrating a method for detecting unplanned events, in accordance with some embodiment of the present disclosure,

[0016] Fig. 6 and Fig. 7 show' exemplary graphs of clustered data based on unplanned events, in accordance with some embodiments of the present disclosure; [0017] Fig, 8 shows a general-purpose computer system for managing merchandise stored in a warehouse, in accordance with embodiments of the present disclosure,

[0018] It should be appreciated by those skilled in the art that any block diagrams herein represent conceptual views of illustrative systems embodying the principles of the present subject matter. Similarly, it may be appreciated that any flow charts, flow diagrams, state transition diagrams, pseudo code, and the like represent various processes which may be substantially represented in computer readable medium and executed by a computer or processor, whether or not such computer or processor is explicitly shown,

DETAILED DESCRIPTION

[0019] In the present document, the word "exemplary" is used herein to mean "serving as an example, instance, or illustration." Any embodiment or implementation of the present subject matter described herein as "exemplary'" is not necessarily to be construed as preferred or advantageous over other embodiments,

[0020] While the disclosure is susceptible to various modifications and alternative forms, specific embodiment thereof has been shown by way of example in the drawings and may be described in detail below. It should be understood, however that it is not intended to limit the disclosure to the particular forms disclosed, but on the contrary, the disclosure is to cover all modifications, equivalents, and alternative falling within the scope of the disclosure.

[0021] The terms “comprises”, “includes” “comprising”, “including” or any other variations thereof, are intended to cover a non-exclusive inclusion, such that a setup, device, or method that comprises a list of components or steps does not include only those components or steps but may include other components or steps not expressly listed or inherent to such setup or device or method. In other words, one or more elements in a system or apparatus proceeded by “comprises... a” or “includes... a” does not, without more constraints, preclude the existence of other elements or additional elements in the system or apparatus. [0022] In the following detailed description of the embodiments of the disclosure, reference is made to the accompanying drawings that form a part hereof, and in which are shown by way of illustration specific embodimentsin which the disclosure may be practiced. These embodiments are described in sufficient detail to enable those skilled in the art to practice the disclosure, and it is to be understood that other embodiments may be utilized and that changes may be made without departing from the scope of the present disclosure. The following description is, therefore, not to be taken in a limiting sense.

[0023] Fig. 1 shows an exemplary environment of a supply chain (100). The supply chain (100) shown in Fig. 1 is simplified to illustrate the embodiments of the present disclosure. As seen, the supply chain (100) comprises an inventory management system (101), a warehouse server (102), one or more merchant servers (103a, 103b) and one or more databases (104a, 104b, 104c). In an embodiment, the warehouse server is associated with a warehouse (not shown) which may house the inventory. The warehouse server (102) may be located inside the warehouse or may be located remotely. In an embodiment, inventory may refer to the products or items present in the warehouse. The warehouse may be associated with a retail business or a manufacturer or a supplier. For example, the warehouse may store electronic items and electrical equipment. Stock may refer to individual item type and unique details about the item. For example an item may refer to mobile phones, and stock may refer to each mobile phone having unique specification such as color, memory, screen size, and the like. Stock is also commonly referred as Stock Keeping Unit (SKIJ) in the retail industry. The one or more merchant servers (103a, 103b) may be associated with one or more merchants (not shown). The one or more merchants may be retailers associated with the manufacturer or supplier. The one or more merchant servers (103a, 103b) may provide the warehouse server (102) information regarding demand of the SKU, sales information, price information, and the like. In an embodiment, the warehouse may be associated with the one or more merchants along with being associated with the supplier or manufacturer.

[0024] The one or more databases (104a, 104b, 104c) may include a warehouse historian, a sales historian, a demand historian, a transport database, a weather database, and a media database. In an embodiment, the one or more database (104a, 104b, 104c) are hosted by respective servers. [0025] The inventory management system (101) may be configured to manage the inventory- present in the warehouse. Managing inventory includes, but not limited to, determine current SKU, determine sales of SKU, determine price calculation for the SKU, estimate demand of SKU, order/ pre-order SKU to meet the demand, and the like. Further, the inventory management system (101 ) may also perform various analytics on data available to optimize the inventory. In an instance, the inventory management system (101) may determine SKU that are likely to have higher demand during a season. For example, Christmas trees, chocolates and gifts are more likely to have higher demand in November- December and less demand during the other months of the year. Likewise, the inventory management system (101 ) may determine demand forecast of the SKU to determine whether inventory_' status (excess inventory or insufficient inventory). Further process such as order or sales may also depend on the demand forecast.

[0026] Demand forecast is a predictive analysis used to predict customer demand to optimize the supply chain (100). Demand forecast uses historical data, statistical techniques or Artificial Intelligence (AI) based techniques such as regression, time-senes prediction, and the like to predict customer demand. For the warehouse, the demand forecast is an important factor for stocking the inventory. For example, the demand forecast may predict that thirty million chocolate boxes are required in New York during Christmas season. Therefore, the inventory management system (101) may plan to stock at least million chocolate during Christmas season. The demand forecast may not be accurate and includes a forecast error value. The forecast error value may be determined using at least one of Mean Absolute Percent Error (MATE) technique, a mean absolute deviation technique, and the like. The person skilled in the art appreciates the use of one or more existing techniques for determining the forecast information and the forecast error value i anddition to the above-mentioned examples. In one embodiment, the forecast error value is computed using the below equation:

[0027] where the forecasted requirement value indicates forecasted/ estimated demand of the one or more SKU and the actual value indicates an actual demand of the one or more SKU. In an embodiment, the forecasted demand is determined based on the quantity of the SKIT being sold by the one or more merchants (103a, 103b).

[0028] In one embodiment, the forecast error value indicates a deviation in estimating a demand of the SKUs from the actual demand. In a first example, the forecast error value of +4.2 indicates an excess inventory as compared to the quantity of the SKUs required according to the actual demand from the customers for the corresponding SKUs. In a second example, the forecast error value of -2.8 indicates that insufficient quantity of the SKUs is stored in the warehouse as compared to the quantity of the SKUs required according to the actual demand.

[0029] The inventory management system (101) generates a demand forecast of the SKU using the one or more databases (104a, 104b, 104c). Conventional systems generates the demand forecast using planned events. Therefore, the forecast error value is large which leads to improper demand forecast. Hence, the inventory management is not optimized and leads to monetary loss, customer dissatisfaction, and wastage. In the present disclosure the inventory management system (101) considers the planned events and one or more unplanned events to generate the demand forecast. The one or more unplanned events are determined using external databases such as, but not limited to the transport database, weather database and media database. A person skilled in the ait will appreciate that the abovementioned database are only exemplary and the present disclosure may include other public and private databases that impact the demand forecast.

[0030] Fig. 2 shows a detailed block diagram of the inventory management system (101), in accordance with some embodiments of the present disclosure.

[0031] The inventory management system (101) may include Central Processing Unit (“CPU” or “processor”) (203) and a memory (202) storing instructions executable by the processor (203). The processor (203) may include at least one data processor for executing program components for executing user (101) or system-generated requests. The memory (202) may be communicatively coupled to the processor (203). The inventory management system (101) further includes an Input/ Output (I/O) interface (201). The I/O interface (201) may be coupled with the processor (203) through which an input signal or/and an output signal may be communicated. In one embodiment, the inventory management system (101) may receive the one or more details, the sales history , and the predefined threshold, through the I/O interface (201).

[0032] In some implementations, inventory management system (101) may include data (204) and sendees (209). As an example, the data (204) and services (209) may be stored in the memory (202). In one embodiment, the data (204) may include, for example, model parameters (205), inventory metrics (206), stock details (207), and other data (208). j0033] In an embodiment, the model parameters (205) may include model coefficients that are used to configure a forecast model to generate the demand forecast. An example of the model parameters (205) may include mean values and median values in case of a statistical model and hyperparameters in case of a machine learning model.

[0034] In an embodiment, the inventory metrics (206) may include inventory cost and pricing, condition of the inventory, quantity of the inventory, inventory acquisition date, purchase of the SKUs, purchase terms and the tike,

[0035] In an embodiment, the stock details (207), SKU category, SKU manufacturer, SKU specification, SKU price and the like.

[0036] In some embodiments, data (204) may be stored in the memory (202) in form of various data structures. Additionally, the data, (204) may be organized using data models, such as relational or hierarchical data models. The other data (208) may store data, including temporary data and temporary files, generated by the services (209) for performing the various functions of the inventory management system (101). The other data (208) may also include the forecast model. The forecast model may include statistical model or machine learning model.

[0037] In some embodiments, the data (204) stored in the memory (202) may be processed by the services (209). The services (209) may be stored within the memory (202). In an example, the sendees (209) communicatively coupled to the processor (203) configured in the inventory management system (102), may also be present outside the memory (202) as shown in Fig. 2 and implemented as hardware. As used herein, the term services (209) may refer to an Application Specific Integrated Circuit (ASIC), a FPGA (Field Programmable Gate Array), an electronic circuit, a processor (203) (shared, dedicated, or group), and memory (202) that execute one or more software or firmware programs, a combinational logic circuit, and/or other suitable components that provide the described functionality. In some other embodiments, the services (209) may be implemented using at least one of ASICs and FPGAs.

[0038| In one implementation, the services (209) may include, for example, a communication service (210), an event detection service (211), a forecast service (212) and other services (213).

10039] In an embodiment, the communication service (210) is configured for obtaining the forecast model from the memory (202). The forecast model may be configured to generate the demand forecast of the SKU in the inventory. In one embodiment, the forecast model may be configured to generate the demand forecast based on planned events. For instance the forecast model utilizes data (204) such as the inventory metrics (206) and the stock details (207) to generate the demand forecast. The communication service (210) may further be configured to receive data from one or more data sources. The one or more data sources may include the one or more databases (104a, 104b, 104c), The communication service (210) may include sendees such as Data Access Service (D AS) required for communicating with the one or more databases (104a, 104b, 104c).

[0040] In an embodiment, the event detection service (21 1) may be configured to detect the one or more planned events and the one or more unplanned events. The event detection service (211) may receive the inventory metrics (206), the stock details (207) and the data from the one or more databases (104a, 104b, 104c) from the communication service (210). The one or more planned events may be detected using the inventory metrics (206), and the stock details (207). Further, the event detection service (211) may use statistical models to determine a trend of planned events. Examples of the one or more planned events may include, but not limited to an annual sales event my a merchant, a festival, an election, sports events and the like, in an embodiment, the event detection service (211) may determine a location of the one or more planners events. The location may be determined using historical data. For example, location of an annual event such as Christmas sale may be obtained from the one or merchant servers (103a, 103b). Likewise, the location of the one or more events may be obtained from known methods. The event detection service (211) may be aware of the one or more planned events, hence may generate the demand forecast considering information available about the one or more planned events. The information available may include historical sales data during historical planned events, historical logistics and manufacturer or retailer data and the like. Further, the event detection sendee (211) may detect the one or more unplanned using the external databases from the one or more databases (104a, 104b, 104c). The one or more unplanned events may include, but are not limited to, a protest, a rally, a natural disaster, a disease outbreak, a lockdown, a curfew' and the like. In an embodiment, the one or more unplanned events may be scheduled at short notice. The event detection sendee (211) detects the one or more unplanned events using the data received from the one or more external databases. The event detection sendee (211) may use statistical techniques and machine learning techniques to detect the one or more unplanned events.

[0041] In an embodiment, the forecast service (212) may be configured to generate demand forecast of the SKUs using the one or more planned events and further generate an updated demand forecast based on the one or more unplanned events. The demand forecast may include predicting sales volume on a daily basis or weekly basis or monthly basis. In an embodiment, the forecast service may also predict price of the SKUs at different points of time. The forecast service (212) may use the forecast model to generate the demand forecast. In an embodiment, the forecast model may implement prediction techniques to generate the demand forecast,

[0042] In an embodiment, the other sendees (213) may include a pricing service, a order management service, a logistic service and the like. The pricing service may manage price of the SKUs based on the predicted price of the SKUs. The order management service may place or cancel SKU orders based on the predicted sales. The logistic service may manage logistics of the SKUs within the warehouse and between warehouses.

[0043] Fig. 3 shows a flowchart illustrating the method of managing the inventory. The order in which the method (300) may be described is not intended to he construed as a limitation, and any number of the described method blocks may be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method may be implemented in any suitable hardware, software, firmware, or combination thereof.

[0044] At step (301) the inventory management system (101) receives a request to produce the demand forecast. In one embodiment, the warehouse server (102) may request the inventory management system (101) to produce the demand forecast. In an embodiment, the inventory management system (101) may receive the request periodically, for example daily, weekly, monthly. In another embodiment, the inventory management system (101) may periodically generate the request to produce the demand forecast.

[0045] At step (302) the inventory management system (101) invokes the forecast service (212) to generate the demand forecast. The steps performed by the forecast service (212) are illustrated in steps (304) - (307). At step (304) the forecast service (212) aggregates the data (204). For example, the forecast service (212) aggregates the inventory metrics (206), the stock details (207) and sales history. In an embodiment, data fusion technique may be used to aggregate the data (204), At step (305), the inventory management system (101) may use segmentation technique to categorize the SKUs. For example, the segmentation technique may include at least one of a Recency-Frequeney-Monetary (RFM) technique, centroid based clustering technique, logistic regression, decision trees, density-based spatial clustering technique, and the like. The person skilled in the art appreciates the use of other segmentation techniques in addition to the above mention examples. In a first example, using the RFM technique, the inventory management system (101) determines the Recency (R), Frequency (F), and Monetary (M) values using the data (204), and the sales history. Further, using the Recency (R), Frequency (F), and Monetary (M) values, the inventory management system (101) categorizes the SKUs into one or more groups. At step (306) the inventory management system (101) generates the demand forecast using a risk index and a value index. The risk index may indicate a risk of having an excess or insufficient inventory and the value index may indicate a value of having an excess or insufficient inventory. Based on risk index and the value index, the inventory management system (101) generates the demand forecast. At step (307), the inventory management system (101) updates the forecast model for generating an updated demand forecast, based on the data collected from the one or more external databases,

[0046] Fig, 4 shows a flowchart illustrating the method of generating the updated forecast model. The order in which the method (400) may be described is not intended to be construed as a limitation, and any number of the described method blocks may be combined in any order to implement the method. Additionally, individual blocks may be deleted from the methods without departing from the spirit and scope of the subject matter described herein. Furthermore, the method may be implemented in any suitable hardware, software, firmware, or combination thereof.

[0047] At step (401), the inventory management system (101) obtains the forecast model that has generated the demand forecast for the SKUs using the data (204). The forecast model may have generated the demand forecast as described in the steps (304) - (306).

[0048] At step (402), the inventory management system (101) receives the data from the one or more external databases from the one or more databases (104a, 104b, 104c). In an embodiment, the one or more external databases may include, the transport database, the media database and the weather database. Examples of transport database may include, a road vehicle traffic database, a ship traffic database, an air traffic database and the like. Examples of media database may include, a news database, a social media database, law and policy databases, market and economy databases and the like. In an example, the inventory management system (101) may receive data from a social media database and a news database about a curfew imposed by a government. The one or more external databases may further include location database and other warehouse database. The location database may provide location information of the one or more planned events. For example, the location database may store locations of events that are planned to occur in a calendar year.

[0049] At step (403), the inventory management system (101) detects the one or more unplanned events using the data received from the one or more external databases. The one or more unplanned events may be unexpected events that impact the sales of the SKUs. Reference is now' made to Fig. 5 which describes the steps of detecting the one or more unplanned events. [0050] At step (501), the inventory management system (101) determines a trend in the data received from the one or more external databases. In an embodiment, the statistical model or machine learning model may be used to determine the trend in the data. In an embodiment, time series data may be analyzed and compared over historical data to identify a pattern of relationship between the data. Clustering techniques such as K-means clustering or hierarchical clustering or self-organizing maps may be used to cluster patterns of data. In an embodiment, big data received from the one or more external databases may be classified using one or more of existing techniques such as Naive Bayer classification technique, Convolution Neural Network (CNN). The classification techniques may be used to determine classes such as trending topics, viral topics, topics that hinder movement of cargo, shipment or impacts sale of the SKUs. The classification techniques may use keywords in the data to classify events. Further, the classified data is then analyzed to determine the one or more unplanned events. For example, Long-Short Term Memory (LSTM) technique may be used to analyze the classified data. In an embodiment, a combination of CNN and Recurrent Neural Network (RNN) may be used to detect the one or more unplanned events. For example, the CNN may be used to identify keywords that are related to an event. Input sentences may be converted to sentence matrix and fed to the CNN. The CNN may implement many filters based on the classification. Thereafter, the LSTM may detect the one or more events. The LSTM may receive the classified data as input and detect anomalies in the data. The LSTM may be trained with normal data and may be further trained to detect anomalies of abnormal data, from input data. For example, the LSTM may detect a vehicle traffic created due to an accident and a vehicle traffic created due to a rally as abnormal trend.

[0051] At step (502), the inventory management system (101) may determine a seasonal index for the trend. Seasonal index may denote whether the determined trend is seasonal or not. In an embodiment, a plurality of seasonal trends may be stored in a seasonal database. A seasonal trend may be an event that may occur repeatedly. For example, festivals may occur annually, sports events may occur monthly, and the inventory management system (101) may compare the determined trend with the plurality of trends stored in the seasonal database. For example, the inventory management system (101) may compare the determined trend of the traffic data with the seasonal database. The seasonal database may comprise a seasonal trend of vehicle traffic during Christmas (during the month of December), Hence, the inventory management system (101) determines of the detected event is seasonal or not. If the event is not present in the seasonal database, then the inventory management system (101) may classify the event as non-seasonal abnormal event.

[0052| At step (503), the inventory management system (101) determines the abnormal event having the anomaly as the unplanned event based on the comparison with the seasonal database.

[0053] Referring back to Fig. 4, at step (404), the inventory management system (101) generates the updated forecast model based on the one or more unplanned events. The inventory' management system (101) determines an impact of the one or more unplanned events on the SKUs in the inventory. The inventory management system (101) may determine impact on the sales of the SKU, impact on the demand of the SKUs, impact on the manufacture of the SKUs, impact on the logistics of the SKUs based on the one or more unplanned events. For example, a maintenance delay in a port may delay shipment of SKUs to the warehouse. Therefore, the inventory may not have sufficient stock to meet the demand of the customers. Likewise, the impact of the one or more unplanned events on the SKUs are determined. Further, the inventory management system (101) generates the updated forecast model based on the impact of the one or more unplanned events on the SKUs, The obtained forecast model is generated using the planned events. The forecast model is then updated by updating the model parameters (205), the inventory metrics (206), and the stock details (207) based on the one or more unplanned events. Thereafter the inventory management system (101) executes the updated forecast model to generate the updated demand forecast. The updated demand forecast is generated based on the unplanned events, which forecasts the sale of the SKUs, the price of the SKUs, the demand of the SKUs. In an embodiment, the updated demand forecast may be generated using a prediction model. In an embodiment, the inventory management system (101) obtains the forecast error value from the obtained forecast model. Further, the inventory management system (101) adjusts the forecast error value based on the impact of the one or more unplanned events on the SKUs. For example, the obtained forecast model may have generated a forecast error value of 4.2 which may indicate that the inventory has excess SKU of 1000 units based on predicted sales. An unplanned event such as a curfew may have big impact on the SKU and the forecast error value may be updated to 4.4 which may indicate that the inventory has excess of 1200 units. Therefore, the adjusted forecast error value provides accurate demand forecast of the stock in the inventory. Further, inventory planning and supply chain management may be based on the adj listed demand forecast,

[0054] Fig. 6 shows an exemplary graph illustrating sales of SKUs due to rainfall. In the Fig. 6 two SKUs (601 and 602) are represented. The SKU (601 a) and the SKU (601 b) are representations of sales before and after rainfall. Likewise, SKU (602a) and the SKU (602b) are representations of sales before and after rainfall. For example, the SKU (601) may be apparels and the SKU (602) may be food items. As can be seen from the Fig. 6, the apparels sales has been impacted after rainfall, whereas the food items sales is not impacted by the rainfall. Hence, the forecast error value associated with the apparels may be updated and the forecast error value of the food items may remain the same. An overall forecast error value may be determined using the updated forecast error value of the apparels and the forecast error value of the food items. Therefore, the amount of apparels that needs to be stocked in the warehouse may be reduced for the period for which rainfall in expected, whereas the food items may be stocked as usual before the rainfall. Hence, inventory and logistic cost may be reduced, thereby optimizing the inventory.

[0055] Fig. 7 shows an exemplar}_' graph illustrating sales of SKUs due to cargo movement. In the Fig. 7 two SKUs (701 and 702) are represented. The SKU (701a) and the SKU (701b) are representations of sales before and after cargo movement. Likewise, SKU (702a) and the SKU (702b) are representations of sales before and after the cargo movement. For example, the SKU (701) may be Christmas gifts and the SKU (702) may be medicines. As can be seen from the Fig. 7, the Christmas gifts sales has not been impacted by the cargo movement, whereas the medicines sales is impacted by the cargo movement. Hence, the forecast error value associated with the Christmas gifts may remain the same and the forecast error value of the medicines may be updated same.

[0056] The present disclosure enables optimizing inventory and supply chain by adjusting the demand forecast accurately. Using the one or more external databases to generate the demand forecast, customer demand is met, thereby increasing customer satisfaction. SKU wastage and additional cost is avoided by better inventory' planning. [0057] Fig, 8 illustrates a block diagram of an exemplary computer system (800) for implementing embodiments consistent with the present disclosure. In an embodiment, the computer system (800) may represent the inventory management system (100), The computer system (800) may comprise a central processing unit (“CPU” or “processor”) (802) which corresponds to the processor (203) of Fig. 2, The processor (802) may comprise at least one data processor for executing program components for dynamic resource allocation at run time. The processor (802) may include specialized processing units such as integrated system (bus) controllers, memory (805) management control units, floating point units, graphics processing units, digital signal processing units, etc. The memory (805) may correspond to the memory (202). Fig. 8 illustrates that the inventory management system (101) may be implemented as a general purpose computer system (800).

[0058] The processor (802) may be disposed in communication with one or more input/output (I/O) devices (not shown) via I/O interface (801) which may correspond to the I/O interface (201). The I/O interface (801) may employ communication protocols/niethods such as, without limitation, audio, analog, digital, monoaural, RCA, stereo, IEEE-(1394), serial bus, universal serial bus (USB), infrared, PS/2, BNC, coaxial, component, composite, digital visual interface (DVI), high-definition multimedia interface (HDMI), RF antennas, S-Video, VGA, IEEE 8Q2.n /b/g/n/x, Bluetooth, cellular (e.g., code-division multiple access (CDMA), high-speed packet access (HSPA+), global system for mobile communications (GSM), long-term evolution (I..TE), WiMax, or the like), etc,

[0059] Using the I/O interface (801), the computer system (800) may communicate with one or more I/O devices. For example, the input device (810) may be an antenna, keyboard, mouse, joystick, (infrared) remote control, camera, card reader, fax machine, dongle, biometric reader, microphone, touch screen, touchpad, trackball, stylus, scanner, storage device, transceiver, video device/source, etc. The output device (811) may be a printer, fax machine, video display (e.g., cathode ray tube (CRT), liquid crystal display (LCD), light-emitting diode (LED), plasma, Plasma display panel (PDP), Organic light-emitting diode display (OLED) or the like), audio speaker, etc. Fr example, the display may be used to display the demand forecast of stock. [0060] In some embodiments, the computer system (800) is connected to the service operator through a communication network (809). The processor (802) may be disposed in communication with the communication network (809) via a network interface (803). The network interface (803) may communicate with the communication network (809). The network interface (803) may employ connection protocols including, without limitation, direct connect, Ethernet (e.g., twisted pair 10/100/1000 Base T), transmission control protoeol/Internet protocol (TCP/IP), token ring, IEEE 802.11a/b/g/n/x, etc. The communication network (809) may include, without limitation, a direct interconnection, e-commerce network, a peer to peer (P2P) network, local area network (LAN), wide area network (WAN), wireless network (e.g., using Wireless Application Protocol), the Internet, Wi-Fi, etc. Using the network interface (803) and the communication network (809), the computer system (800) may communicate with the one or more service operators. For example, the computer system (800) may communicate with the warehouse server (102), the merchant server (103a, 103b) and the one or databases (104a, 104b, 104c) via one or more of the abovementioned communication technologies.

[0061] In some embodiments, the processor (802) may be disposed in communication with a memory (805) (e.g,, RAM, ROM, etc. not shown in Figure 8 via a storage interface (804), The storage interface (804) may connect to memory' (805) including, without limitation, memory drives, removable disc drives, etc., employing connection protocols such as serial advanced technology attachment (SATA), Integrated Drive Electronics (IDE), IEEE- 1394, Universal Serial Bus (USB), fiber channel, Small Computer Systems Interface (SCSI), etc. The memory drives may further include a drum, magnetic disc drive, magneto-optical drive, optical drive, Redundant Array of Independent Discs (RAID), solid-state memory devices, solid-state drives, etc.

[0062] The memory (805) may store a collection of program or database (104) components, including, without limitation, user interface (806), an operating system (807), web server (808) etc. In some embodiments, computer system (800) may store user/application data (806), such as the data, variables, records, etc. as described in this disclosure. Such databases may he implemented as fault-tolerant, relational, scalable, secure databases such as Oracle or Sybase. For example, the memory (805) may store the data (204). [0063] The operating system (807) may facilitate resource management and operation of the computer system (800). Examples of operating systems include, without limitation, APPLE® MACINTOSH® OS X®, UNIX®, UNIX-like system distributions (E.G., BERKELEY SOFTWARE DISTRIBUTION® (BSD), FREEBSD®, NETBSD®, OPENBSD, etc.), LINUX® DISTRIBUTIONS (E.G., RED HAT^'®, UBUNTU®, KUBUNTU®, etc,), IBM®OS/2®, MICROSOFT® WINDOWS® (XP®, VISTA®/7/8, 10 etc.), APPLE® IOS®, GOOGLETM ANDROIDTM, BLACKBERRY® OS, or the like.

[0064] In some embodiments, the computer system (800) may implement a web browser (not shownin Fig. 8) stored program component. The web browser may be a hypertext viewing application, such as MICROSOFT® INTERNET EXPLORER®, GOOGLETM CHROME TM, MOZILLA® FIREFOX®, APPLE® SAFARI®, etc, Secure web browsing may be provided using Secure Hypertext Transport Protocol (HTTPS), Secure Sockets Layer (SSL), Transport Layer Security (TIN), etc. Web browsers (808) may utilize facilities such as AJAX, DHTML, ADOBE® FLASH®, JAVASCRIPT ® , JAVA®, Application Programming Interfaces (APIs), etc. In some embodiments, the computer system (800) may implement a mail server stored program component. The mail server may be an Internet mail server such as Microsoft Exchange, or the like. The mail server may utilize facilities such as Active Server Pages (ASP), ACTIVEX®, ANSI® C-H7C#, MICROSOFT®, .NET, CGI SCRIPTS, JAVA·®, JAVASCRIPT®, PERL®, PHP, PYTHON®, WEBOBXECTS®, etc. The mail server may utilize communication protocols such as Internet Message Access Protocol (IMAP), Messaging Application Programming Interface (MAPI), MICROSOFT® Exchange, Post Office Protocol (POP), Simple Mail Transfer Protocol (SMTP), or the like. In some embodiments, the computer system (800) may implement a mail client stored program component. The mail client may be a mail viewing application, such as APPLE® MAIL, MICROSOFT® ENTOURAGE®, MICROSOFT® OUTLOOK®, MOZILLA® THUNDERBIRD®, etc,

[0065] Furthermore, one or more computer-readable storage media may be utilized m implementing embodiments consistent with the present invention. A computer-readable storage medium refers to any type of physical memory (805) on which information or data readable by a processor (802) may be stored. Thus, a computer-readable storage medium may store instructions for execution by one or more processors, including instructions for causing the processors to perform steps or stages consistent with the embodiments described herein. The term “computer- readable medium” should be understood to include tangible items and exclude carrier waves and transient signals, i.e., non-transitory. Examples include Random Access memory (RAM), Read- Only memory (ROM), volatile memory, non-volatile memory, hard drives, Compact Disc (CD) ROMs, Digital Video Disc (DVDs), flash drives, disks, and any other known physical storage media. In an embodiment, the computer system (800) may comprise remote devices (812). For example, the remote devices (812) may include, but not limited to the warehouse server (102) and the one or more merchant servers (103a, 103b), and the one or more database servers hosting the one or more databases (104a, 104b, 104c).

[0066] The terms "an embodiment", "embodiment", "embodiments", "the embodiment", "the embodiments", "one or more embodiments", "some embodiments", and "one embodiment" mean "one or more (but not all) embodiments of the invention(s)" unless expressly specified otherwise.

[0067] The terms "including", "comprising", “having” and variations thereof mean "including but not limited to", unless expressly specified otherwise.

[0068] The enumerated listing of items does not imply that any or all of the items are mutually exclusive, unless expressly specified otherwise. The terms "a", “an" and “the" mean “one or more", unless expressly specified otherwise.

[0069] A description of an embodiment with several components in communication with each other does not imply that all such components are required. On the contrary, a variety of optional components are described to illustrate the wide variety of possible embodiments of the invention.

[0070] When a single device or article is described herein, it may be readily apparent that more than one device/article (whether or not they cooperate) may be used in place of a single device/article. Similarly, where more than one device or article is described herein (whether or not they cooperate), it may be readily apparent that a single device/article may be used in place of the more than one device or article or a different number of devices/articles may be used instead of the shown number of devices or programs. The functionality and/or the features of a device may be alternatively embodied by one or more other devices which are not explicitly described as having such functional ity/features. Thus, other embodiments of the invention need not include the device itself. j0071] The illustrated operations of Fig, 3, Fig. 4, Fig. 5 show certain events occurring i an certain order. In alternative embodiments, certain operations may be performed in a different order, modified, or removed. Moreover, steps may be added to the above described logic and still conform to the described embodiments. Further, operations described herein may occur sequentially or certain operations may be processed in parallel. Yet further, operations may be performed by a single processing unit or by distributed processing units.

[0072] Finally, the language used in the specification has been principally selected for readability and instructional purposes, and it may not have been selected to delineate or circumscribe the inventive subject matter. It is therefore intended that the scope of the invention be limited not by this detailed description, but rather by any claims that issue on an application based here on. Accordingly, the disclosure of the embodiments of the invention is intended to be illustrative, but not limiting, of the scope of the invention, which is set forth in the following claims.

[0073] While various aspects and embodiments have been disclosed herein, other aspects and embodiments may be apparent to those skilled in the art. The various aspects and embodiments disclosed herein are for purposes of illustration and are not intended to be limiting, with the true scope and spirit being indicated by the following claims.

Claims

We claim:

1. A method of managing an inventory in a supply chain, comprising: obtaining, by a system, a forecast model for generating a demand forecast of stockin the inventory, wherein the forecast model is derived based on one or more planned events, using one or more supply chain data sources; receiving, by the system, data from one or more data sources at regular time intervals, wherein the one or more data sources are external to the supply chain; detecting, by the system, one or more unplanned events based on the data from the one or more data sources; and generating, by the system, an updated demand forecast of the stock in the inventory' using the forecast model and the one or more unplanned events, for managing the inventory, wherein the one or more unplanned events are fed to the forecast model.

2. The method of claim 1 , wherein the one or more data sources includes at least one of, a weather server, a transport server, and a media server.

3. The method of claim 1, wherein the data from the one or more data sources includes at least one of, transport data, weather data, news data,, and social media data.

4. The method of claim 1, wherein detecting the one or more unplanned events comprises: determining a trend in the data received from the one or more external sources using one or more clustering techniques; determining a seasonal index for the trend using a seasonal trend database; detecting an anomaly in the trend based on the data received from the one or more external sources and the seasonal index, wherein the anomaly in the trend is characterized as one or more unplanned events.

5. The method of claim 1, wherein generating the updated demand forecast of the stock comprises: determining an impact of the one or more unplanned events on the stock in the inventory; generating an updated forecast model using the impact of the one or more unplanned events; and executing the updated forecast model for generating the updated demand forecast of the stockin the inventory.

6. The method of claim 5, wherein generating the updated forecast model comprises: obtaining a forecast error value from the forecast model, wherein the forecast error value is indicative of an opportunity loss or excess stock; and adjusting the forecast error value based on the one or more unplanned events; and updating one or more model parameters based on updated forecast error value to generate the updated forecast model.

7. A system for managing an inventor_}' in a supply chain, comprising: a memory; and one or more processors, configured for: obtaining a forecast model for generating a demand forecast of stock in the inventory, wherein the forecast model is derived based on one or more planned events, using one or more supply chain data sources; receiving data from one or more data sources at regular time intervals, wherein the one or more data sources are external to the supply chain; detecting one or more unplanned events based on the data from the one or more data, sources; and generating an updated demand forecast of the stock in the inventor}' using the forecast model and the one or more unplanned events, for managing the inventory, wherein the one or more unplanned events are fed to the forecast model.

8. The system of claim 7, wherein the one or more data sources includes at least one of, a weather server, a transport server, and a media server.

9. The system of claim 7, wherein the one or more processors are configured for detecting the one or more unplanned events by: determining a trend in the data received from the one or more external sources using one or more clustering techniques; determining a seasonal index for the trend using a seasonal trend database; detecting an anomaly in the trend based on the data received from the one or more external sources and the seasonal index, wherein the anomaly in the trend is characterized as one or more unplanned events.

10. The system of claim 7, wherein the one or more processors are configured for forecasting the stock by: determining an impact of the one or more unplanned events on the stock in the inventor}_'; generating an updated forecast model using the impact of the one or more unplanned events; wherein generating the updated forecast mode comprises: obtaining a forecast error value from the forecast model, wherein the forecast error value is indicative of an opportunity loss or excess stock; and adjusting the forecast error value based on the one or more unplanned events; and updating one or more model parameters based on updated forecast error value to generate the updated forecast model, and executing the updated forecast model for forecasting the stock in the inventory.