CN111461866B - Data analysis method and device - Google Patents
Data analysis method and device Download PDFInfo
- Publication number
- CN111461866B CN111461866B CN202010246737.7A CN202010246737A CN111461866B CN 111461866 B CN111461866 B CN 111461866B CN 202010246737 A CN202010246737 A CN 202010246737A CN 111461866 B CN111461866 B CN 111461866B
- Authority
- CN
- China
- Prior art keywords
- consumption
- target object
- time period
- information
- consumption information
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q40/00—Finance; Insurance; Tax strategies; Processing of corporate or income taxes
- G06Q40/03—Credit; Loans; Processing thereof
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
- G06N20/10—Machine learning using kernel methods, e.g. support vector machines [SVM]
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Business, Economics & Management (AREA)
- Software Systems (AREA)
- General Physics & Mathematics (AREA)
- Finance (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Accounting & Taxation (AREA)
- Artificial Intelligence (AREA)
- Strategic Management (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Medical Informatics (AREA)
- Technology Law (AREA)
- Marketing (AREA)
- Economics (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computational Linguistics (AREA)
- General Health & Medical Sciences (AREA)
- Molecular Biology (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a data analysis method, which comprises the following steps: the consumption prediction model is trained in advance through consumption information of the target object in a third time period and basic information of a user to which the target object belongs, consumption information of the target object in a second time period is predicted based on the consumption prediction model and the consumption information of the target object in the first time period and the basic information of the user to which the target object belongs, similarity between real consumption information of the target object in the second time period and the predicted consumption information is calculated, and whether abnormal consumption conditions of the target object occur is determined based on the similarity. Therefore, the method predicts whether the consumption behavior of the target object is abnormal, so that the borrowed risk possibly occurring in the credit card can be found in time, and the risk born by the bank is reduced as much as possible.
Description
Technical Field
The present invention relates to the field of finance, and in particular, to a data analysis method and apparatus.
Background
With the improvement of living standard and the transition of consumption concept, credit cards are becoming one way for people to consume. When a bank issues a credit card, the bank sets the credit card amount based on the repayment capability of the customer in order to reduce the risk.
However, in real life, there is often a case where a credit card is borrowed to another person, and this action is likely to increase the repayment pressure of the customer, so that the customer cannot repayment on time, which in any case increases the risk of the bank.
Disclosure of Invention
In view of the above, the embodiment of the invention discloses a data analysis method and a data analysis device, which predict whether the risk of abnormal consumption occurs or not through analysis of credit card consumption conditions.
The embodiment of the invention discloses a data analysis method, which comprises the following steps:
acquiring historical consumption information of a target object in a preset first time period and basic information of a user to whom the target object belongs; the target object is a lending product;
predicting the consumption condition of the target object in a second time period based on the historical consumption information of the target object in the first time period, the basic information of the user to which the target object belongs and a preset consumption prediction model; the consumption prediction model is obtained by training a preset machine learning model through historical consumption data of a target object in a third time period and basic information of a user to which the target object belongs;
obtaining real consumption information of a target object in a second time period;
calculating the similarity between the real consumption information of the target object in the second time period and the consumption information predicted in the second time period;
and determining whether the consumption behavior of the target object is abnormal or not based on the relation between the similarity and a preset threshold value.
Optionally, the training process of the consumption prediction model includes:
constructing a neural network model;
acquiring historical consumption data of a target object in a third time period and basic information of a user to which the target object belongs;
determining an initial value of a parameter of the neural network;
and training the neural network model based on the historical consumption data of the target object in the third time period, the basic information of the user to which the target object belongs and the initial value of the parameters of the neural network.
Optionally, the calculating the similarity between the real consumption information and the predicted consumption information of the target object in the second time period includes:
determining a matching result of each consumption object contained in the second time period real consumption information and the consumption object contained in the consumption information predicted by the second time period under the condition that the second time period real consumption information comprises at least one consumption object;
and calculating the similarity of the real consumption information of the user in the second time period and the predicted consumption information based on the matching result of each consumption object contained in the real consumption information in the second time period and the consumption object contained in the predicted consumption information in the second time period.
Optionally, the determining a matching result between each consumption object included in the real consumption information of the second time period and the consumption object included in the predicted consumption information of the second time period includes:
constructing an evaluation function between a consumption object contained in the real consumption information of the second time period and a consumption object contained in the consumption information predicted by the second time period;
and determining whether each consumption object contained in the real consumption information of the second time period is matched with the consumption object contained in the predicted consumption information of the second time period based on the evaluation function, and obtaining a matching result.
Optionally, the determining whether the consumption behavior of the user is abnormal based on the relationship between the similarity and the preset threshold includes:
if the similarity is larger than a preset threshold value, the consumption behavior of the user is indicated to be abnormal;
and if the similarity is smaller than or equal to a preset threshold value, the consumption behavior of the user is abnormal.
Optionally, in the case that the actual consumption situation of the second period of time includes at least one consumption object, the method further includes:
determining a total number of consumption objects included in the real consumption situation of the second time period;
a threshold is determined based on a total number of consumption objects included in the real consumption situation for the second period of time.
Optionally, the method further comprises:
under the condition that the consumption abnormal behavior of the target object is detected, monitoring the use dynamic state of the target object;
when the target object is used again, acquiring face information of a consumer using the target object;
judging whether the face information of the consumer is consistent with the face information of the user to which the target object belongs;
and if the face information of the consumer is inconsistent with the face information of the user to which the target object belongs, sending a consumption abnormality reminder to the user to which the target object belongs.
The embodiment of the invention also discloses a data analysis device, which comprises:
the first acquisition unit is used for acquiring consumption information of the target object in a first time period and basic information of a user to which the target object belongs; the target object is a lending product; the target object is a lending product;
the prediction unit is used for predicting the consumption information of the target object in the second time period based on the consumption information of the target object in the first time period, the basic information of the user to which the target object belongs and a preset consumption prediction model; the consumption prediction model is obtained by training a preset machine learning model through consumption information of the target object in a third time period and basic information of a user to which the target object belongs;
the second acquisition unit is used for acquiring real consumption information of the target object in a second time period;
the similarity calculation unit is used for calculating the similarity between the real consumption information of the target object in the second time period and the consumption information predicted in the second time period;
and the abnormal behavior determining unit is used for determining whether the consumption behavior of the target object is abnormal or not based on the relation between the similarity and a preset threshold value.
Optionally, the similarity calculation unit includes:
a matching result determining unit, configured to determine, in a case where the second period of real consumption information includes at least one consumption object, a matching result of each consumption object included in the second period of real consumption information and a consumption object included in the consumption information predicted by the second period of time;
and the similarity calculation unit is used for calculating the similarity of the real consumption information of the user in the second time period and the predicted consumption information based on the matching result of each consumption object contained in the real consumption information in the second time period and the consumption object contained in the predicted consumption information in the second time period.
Optionally, the matching result determining unit includes:
the evaluation function construction unit is used for constructing an evaluation function between the consumption objects contained in the consumption information which is true in the second time period and the consumption objects contained in the consumption information which is predicted in the second time period;
and the matching result determining subunit is used for determining whether each consumption object contained in the real consumption information of the second time period is matched with the consumption object contained in the consumption information predicted by the second time period based on the evaluation function, so as to obtain a matching result.
The embodiment of the invention discloses a data analysis method, which comprises the following steps: the consumption prediction model is trained in advance through consumption information of a target object in a third time period and basic information of a user to which the target object belongs, consumption information of the target object in a second time period is predicted based on the consumption prediction model and the consumption information of the target object in the first time period and the basic information of the user to which the target object belongs, similarity between real consumption information of the target object in the second time period and the predicted consumption information is calculated, and whether abnormal consumption conditions of the target object occur is determined based on the similarity. Therefore, the method predicts whether the consumption behavior of the target object is abnormal, so that the borrowed risk possibly occurring in the credit card can be found in time, and the risk born by the bank is reduced as much as possible.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings that are required to be used in the embodiments or the description of the prior art will be briefly described below, and it is obvious that the drawings in the following description are only embodiments of the present invention, and that other drawings can be obtained according to the provided drawings without inventive effort for a person skilled in the art.
Fig. 1 shows a flow chart of a data analysis method according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of a method for calculating similarity according to an embodiment of the present invention;
FIG. 3 is a schematic flow chart of a training method of a consumption prediction model according to an embodiment of the present invention;
fig. 4 shows a schematic structural diagram of a data analysis device according to an embodiment of the present invention.
Detailed Description
The following description of the embodiments of the present invention will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present invention, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the invention without making any inventive effort, are intended to be within the scope of the invention.
Referring to fig. 1, a flow chart of a data analysis method provided by an embodiment of the present invention is shown, and in this embodiment, the method includes:
s101: acquiring consumption information of a target object in a first time period and basic information of a user to which the target object belongs; the target object is a lending product;
in this embodiment, the debit product includes a credit card, or other credit product that may enable installment.
In this embodiment, the consumption information of the target object in the first period may be understood as consumption information of the target object in a certain period of time in the history time. Wherein the consumption information includes goods purchased by the user through the target object, and the consumption data may be represented as goods purchased by the user through the credit card, for example. The basic information of the user to which the target object belongs may include, for example: user age, family condition, academic, income level, hobbies, etc.
S102: predicting the consumption information of the target object in a second time period based on the consumption information of the target object in the first time period, the basic information of a user to which the target object belongs and a preset consumption prediction model; the consumption prediction model is obtained by training a preset machine learning model through consumption information of the target object in a third time period and basic information of a user to which the target object belongs;
in this embodiment, the third period of time is represented as a certain period of time within the history time, and the first period of time is represented as a period of time to be predicted. Wherein the third time period is earlier than the first time period.
Illustrating: if consumption of 9 months in 2020 is to be predicted for a user, the second time period may be understood as 9 months in 2020, the first time period and the third time period are each historical time periods earlier than 9 months, and the third time period is earlier than the first time period, for example, the first time period may be a time period of 1 month to 7 months in 2020, and the second time period may be 8 months in 2020.
In this embodiment, the consumption prediction model is obtained by training a preset machine learning model through historical consumption information of the target object in the third time period and basic information of a user to which the target object belongs. The preset machine learning model can be any model capable of predicting the consumption situation through training. In this embodiment, the machine learning model is not limited, and may be a convolutional neural network model, an SVM model, or a random forest model.
The specific training process of the preset machine learning model will be described in detail below, and will not be described in detail in this embodiment.
S103, obtaining real consumption information of the target object in a second time period;
in this embodiment, the actual consumption information in the second period of time is expressed as the actual consumption condition of the target object in the second period of time.
Illustrating: if the target object is a credit card, the consumption information can be obtained through a consumption record of the credit card, and then the real consumption information in the second time period can be obtained through a consumption record of the credit card in the second time period.
S104: calculating the similarity between the real consumption information of the target object in the second time period and the consumption information predicted in the second time period;
in this embodiment, the similarity between the real consumption information and the predicted consumption information may be calculated in various manners, which is not limited in this embodiment.
In this embodiment, preferably, the similarity between the real consumption information and the predicted consumption information of the target object in the second time period may be calculated by the following manner, and specifically, referring to fig. 2, a flowchart of a similarity calculating method provided by the embodiment of the present invention is shown.
S201: determining a matching result of each consumption object contained in the second time period real consumption information and the consumption object contained in the consumption information predicted by the second time period under the condition that the second time period real consumption information comprises at least one consumption object;
s202: and calculating the similarity of the real consumption information of the user in the second time period and the predicted consumption information based on the matching result of each consumption object contained in the real consumption information in the second time period and the consumption object contained in the predicted consumption information in the second time period.
In this embodiment, the consumption object may be understood as: merchandise purchased through the target object, for example, merchandise purchased through a credit card by the user.
In this embodiment, the matching result of the commodity actually consumed and purchased by the user in the second time period and the commodity predicted to be possibly purchased in the second time period may be determined, where the matching result may include the following two cases:
the consumption object included in the real consumption information of the target object in the second time period can be matched with the consumption object included in the predicted consumption information;
that is, the target object is able to match the merchandise actually consumed and purchased with the predicted possible merchandise within the second time period;
illustrating: the commodity really consumed and purchased by the user through the credit card in the second time period comprises the following components: if the sports shoes include sports shoes among commodities which the user predicted to be likely to purchase in the second period of time through the historical consumption data, the sports shoes can be considered as follows: the merchandise that the user actually consumes to purchase during the second time period is matched with merchandise that the predicted user is likely to purchase during the second time period.
Secondly, the consumption object included in the real consumption information of the target object in the second time period is not matched with the consumption object included in the predicted consumption information;
illustrating: if the target object includes the real information in the second time period: the jewelry, if the consumption information predicted by the consumption information in the first time period does not contain jewelry commodities, is considered as: the real consumption information of the target object in the second time period includes consumption objects which are not matched with the consumption objects included in the predicted consumption information.
In this embodiment, the matching result of each consumption object included in the real consumption information of the second time period and the consumption object included in the consumption information predicted by the second time period may be calculated in various manners, which is not limited in this embodiment.
Preferably, a method for calculating a matching result of each consumption object included in the real consumption information of the second period with the consumption object included in the consumption information predicted by the second period may be adopted, including:
constructing an evaluation function between a consumption object contained in the real consumption information of the second time period and a consumption object contained in the consumption information predicted by the second time period;
and determining whether each consumption object contained in the real consumption information of the second time period is matched with the consumption object contained in the predicted consumption information of the second time period based on the evaluation function, and obtaining a matching result.
In this embodiment, for convenience of explanation, a consumption object included in the real consumption information of the second period may be represented as a first object, and a consumption object included in the consumption information predicted in the second period may be represented as a second object.
In this embodiment, the similarity is calculated by the degree of matching between the first object and the second object, and in principle, it can be considered that the more the first object can be matched with the second object, the higher the similarity is represented.
Illustrating: and for the calculation of the similarity, under the condition that the first object and the second object can be matched, the similarity is added, if the first object cannot be matched with the second object, the similarity is reduced, and after all the first objects are traversed, the final similarity is obtained.
S105: and determining whether the consumption behavior of the user is abnormal or not based on the relation between the similarity and a preset threshold value.
Wherein, since the similarity is related to the consumption objects in the real consumption situation, the consumption objects in the real consumption situation are continuously changed in different scenes or different time periods, and the change includes a change of the number of the consumption objects. Therefore, in the case that the number of consumption objects included in the actual consumption situation is changed, if the preset threshold value is not changed, the accuracy of the calculated similarity result will be affected, and in order to improve the accuracy of the final determination result, the preset threshold value may be changed based on the change of the number of consumption objects included in the actual consumption situation, based on this, the embodiment further includes:
determining a total number of consumption objects included in the real consumption information of the second time period;
the threshold is determined based on a total number of consumption objects included in the real consumption information for the second period of time.
In this embodiment, based on the relationship between the similarity and the preset threshold, the determining whether the consumption behavior of the user is abnormal includes two cases as follows:
if the similarity is larger than a preset threshold, the consumption behavior of the user is indicated to be abnormal;
if the similarity is smaller than or equal to a preset threshold value, the consumption behavior of the user is abnormal.
For the credit card, if the consumption behavior of the user is abnormal, the current credit card can be considered to have the risk of being used by others.
In this embodiment, when detecting that the target object has abnormal consumption behavior, face information of a consumer is obtained when detecting that the target object is used again; identifying face information of a consumer, and judging whether the face information of the consumer is consistent with face information of a user to which a target object belongs; if the consumer information is inconsistent with the user information of the target object, verifying whether the consumer accords with a preset identity.
The preset identity may include: the user to whom the target object belongs sets a person capable of consuming the target object or a person belonging to third generation relatives with the user to whom the target object belongs.
If the consumer is detected not to be the user of the target object and the consumer does not accord with the preset identity, sending a consumption abnormality reminder to the user of the target object.
In this embodiment, when it is detected that the credit card is consumed again, face information of the consumer may be obtained by retrieving a camera of the shop.
In this embodiment, a consumption prediction model is trained in advance through consumption information of a target object in a third time period and basic information of a user to which the target object belongs, consumption information of the target object in a second time period is predicted based on the consumption prediction model and the consumption information of the target object in the first time period and the basic information of the user to which the target object belongs, similarity between actual consumption information of the target object in the second time period and the predicted consumption information is calculated, and whether abnormal consumption conditions of the target object occur is determined based on the similarity. Therefore, the method predicts whether the consumption behavior of the target object is abnormal, so that the borrowed risk possibly occurring in the credit card can be found in time, and the risk born by the bank is reduced as much as possible.
Referring to fig. 3, a flowchart of a training method of a consumption prediction model according to an embodiment of the present invention is shown, where in this embodiment, the method includes:
s301: constructing a neural network model;
in this embodiment, the neural network model may be constructed in a plurality of ways, and in this embodiment, the neural network model is not limited, and may be, for example, a deep convolutional neural network model.
S302: acquiring historical consumption data of a target object in a third time period and basic information of a user to which the target object belongs;
s303: determining an initial value of a parameter of the neural network;
in this embodiment, the initial values of the parameters of different neural networks are different, and the initial values of the parameters of the neural networks are determined based on actual conditions.
Illustrating: parameters of the neural network may include: weights and thresholds, the technician may empirically set initial values for the weights and thresholds of the neural network.
S304: and training the neural network model based on the historical consumption data of the target object in the third time period, the basic information of the user to which the target object belongs and the initial value of the parameters of the neural network.
In this embodiment, the neural network is trained by training samples (the training samples include historical consumption information of the target object and basic information of a user to which the target object belongs). In the training process, parameters of the neural network model are continuously changed, and when the most parameters are obtained, the neural network model training is finished, and a trained consumption prediction model is obtained.
Referring to fig. 4, a schematic structural diagram of a data analysis device according to an embodiment of the present invention is shown, where in this embodiment, the device includes:
a first obtaining unit 401, configured to obtain consumption information of a target object in a first period of time and basic information of a user to which the target object belongs; the target object is a lending product;
a prediction unit 402, configured to predict consumption information of a target object in a second time period based on consumption information of the target object in the first time period, basic information of a user to which the target object belongs, and a preset consumption prediction model; the consumption prediction model is obtained by training a preset machine learning model through consumption information of the target object in a third time period and basic information of a user to which the target object belongs;
a second obtaining unit 403, configured to obtain real consumption information of the target object in a second period;
a similarity calculating unit 404, configured to calculate a similarity between the real consumption information of the target object in the second time period and the consumption information predicted in the second time period;
an abnormal behavior determining unit 405, configured to determine whether the consumption behavior of the target object is abnormal based on the relationship between the similarity and a preset threshold.
Optionally, the similarity calculation unit includes:
a matching result determining unit, configured to determine, in a case where the second period of real consumption information includes at least one consumption object, a matching result of each consumption object included in the second period of real consumption information and a consumption object included in the consumption information predicted by the second period of time;
and the similarity calculation unit is used for calculating the similarity of the real consumption information of the user in the second time period and the predicted consumption information based on the matching result of each consumption object contained in the real consumption information in the second time period and the consumption object contained in the predicted consumption information in the second time period.
Optionally, the matching result determining unit includes:
the evaluation function construction unit is used for constructing an evaluation function between the consumption objects contained in the consumption information which is true in the second time period and the consumption objects contained in the consumption information which is predicted in the second time period;
and the matching result determining subunit is used for determining whether each consumption object contained in the real consumption information of the second time period is matched with the consumption object contained in the consumption information predicted by the second time period based on the evaluation function, so as to obtain a matching result.
Optionally, the abnormal behavior determining unit includes:
the first abnormal behavior determination subunit is configured to indicate that the consumption behavior of the user is not abnormal if the similarity is greater than a preset threshold;
and the second abnormal behavior determination subunit is used for indicating that the consumption behavior of the user is abnormal if the similarity is smaller than or equal to a preset threshold value.
Optionally, the method further comprises:
the consumption prediction model training unit is used for:
constructing a neural network model;
acquiring historical consumption data of a target object in a third time period and basic information of a user to which the target object belongs;
determining an initial value of a parameter of the neural network;
and training the neural network model based on the historical consumption data of the target object in the third time period, the basic information of the user to which the target object belongs and the initial value of the parameters of the neural network.
Optionally, the method further comprises:
a threshold determining unit configured to:
determining a total number of consumption objects included in the real consumption information of the second time period;
the threshold is determined based on a total number of consumption objects included in the real consumption information for the second period of time.
Optionally, the method further comprises:
the monitoring unit is used for monitoring the use dynamics of the target object under the condition that the consumption abnormal behavior of the target object is detected;
a face information acquisition unit configured to acquire face information of a consumer who uses the target object when it is monitored that the target object is used again;
the verification unit is used for judging whether the face information of the consumer is consistent with the face information of the user to which the target object belongs;
and the reminding unit is used for sending a consumption abnormality reminder to the user to which the target object belongs if the face information of the consumer is inconsistent with the face information of the user to which the target object belongs.
According to the device, a consumption prediction model is trained in advance through consumption information of a target object in a third time period and basic information of a user to which the target object belongs, consumption information of the target object in a second time period is predicted based on the consumption prediction model and the consumption information of the target object in the first time period and the basic information of the user to which the target object belongs, similarity between real consumption information of the target object in the second time period and the predicted consumption information is calculated, and whether abnormal consumption conditions of the target object occur is determined based on the similarity. Therefore, the method predicts whether the consumption behavior of the target object is abnormal, so that the borrowed risk possibly occurring in the credit card can be found in time, and the risk born by the bank is reduced as much as possible. It should be noted that, in the present specification, each embodiment is described in a progressive manner, and each embodiment is mainly described as different from other embodiments, and identical and similar parts between the embodiments are all enough to be referred to each other.
The previous description of the disclosed embodiments is provided to enable any person skilled in the art to make or use the present invention. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the generic principles defined herein may be applied to other embodiments without departing from the spirit or scope of the invention. Thus, the present invention is not intended to be limited to the embodiments shown herein but is to be accorded the widest scope consistent with the principles and novel features disclosed herein.
Claims (7)
1. A method of data analysis, comprising:
acquiring consumption information of a target object in a first time period and basic information of a user to which the target object belongs; the target object is a lending product;
predicting the consumption information of the target object in a second time period based on the consumption information of the target object in the first time period, the basic information of a user to which the target object belongs and a preset consumption prediction model; the consumption prediction model is obtained by training a preset machine learning model through consumption information of the target object in a third time period and basic information of a user to which the target object belongs;
obtaining real consumption information of a target object in a second time period;
calculating the similarity between the real consumption information of the target object in the second time period and the consumption information predicted in the second time period;
determining whether the consumption behavior of the target object is abnormal or not based on the relation between the similarity and a preset threshold value;
wherein, the determining whether the consumption behavior of the user is abnormal based on the relationship between the similarity and the preset threshold value comprises:
if the similarity is larger than a preset threshold value, the consumption behavior of the user is indicated to be abnormal;
if the similarity is smaller than or equal to a preset threshold value, the consumption behavior of the user is abnormal;
wherein, in case the second period of time real consumption situation comprises at least one consumption object, further comprising:
determining a total number of consumption objects included in the real consumption information of the second time period;
determining a threshold based on a total number of consumption objects included in the real consumption information for the second period of time;
wherein, still include:
under the condition that the consumption abnormal behavior of the target object is detected, monitoring the use dynamic state of the target object;
when the target object is used again, acquiring face information of a consumer using the target object;
judging whether the face information of the consumer is consistent with the face information of the user to which the target object belongs;
and if the face information of the consumer is inconsistent with the face information of the user to which the target object belongs, sending a consumption abnormality reminder to the user to which the target object belongs.
2. The method of claim 1, wherein the training process of the consumption prediction model comprises:
constructing a neural network model;
acquiring historical consumption data of a target object in a third time period and basic information of a user to which the target object belongs;
determining an initial value of a parameter of the neural network;
and training the neural network model based on the historical consumption data of the target object in the third time period, the basic information of the user to which the target object belongs and the initial value of the parameters of the neural network.
3. The method of claim 1, wherein calculating the similarity of the actual consumption information and the predicted consumption information of the target object over the second time period comprises:
determining a matching result of each consumption object contained in the second time period real consumption information and the consumption object contained in the consumption information predicted by the second time period under the condition that the second time period real consumption information comprises at least one consumption object;
and calculating the similarity of the real consumption information of the user in the second time period and the predicted consumption information based on the matching result of each consumption object contained in the real consumption information in the second time period and the consumption object contained in the predicted consumption information in the second time period.
4. The method of claim 3, wherein determining a matching result of each consumption object included in the real consumption information of the second period of time and the consumption object included in the predicted consumption information of the second period of time includes:
constructing an evaluation function between a consumption object contained in the real consumption information of the second time period and a consumption object contained in the consumption information predicted by the second time period;
and determining whether each consumption object contained in the real consumption information of the second time period is matched with the consumption object contained in the predicted consumption information of the second time period based on the evaluation function, and obtaining a matching result.
5. A data analysis device, comprising:
the first acquisition unit is used for acquiring consumption information of the target object in a first time period and basic information of a user to which the target object belongs; the target object is a lending product; the target object is a lending product;
the prediction unit is used for predicting the consumption information of the target object in the second time period based on the consumption information of the target object in the first time period, the basic information of the user to which the target object belongs and a preset consumption prediction model; the consumption prediction model is obtained by training a preset machine learning model through consumption information of the target object in a third time period and basic information of a user to which the target object belongs;
the second acquisition unit is used for acquiring real consumption information of the target object in a second time period;
the similarity calculation unit is used for calculating the similarity between the real consumption information of the target object in the second time period and the consumption information predicted in the second time period;
an abnormal behavior determining unit, configured to determine whether the consumption behavior of the target object is abnormal based on the relationship between the similarity and a preset threshold;
the abnormal behavior determining unit is specifically configured to indicate that the consumption behavior of the user is not abnormal if the similarity is greater than a preset threshold; if the similarity is smaller than or equal to a preset threshold value, the consumption behavior of the user is abnormal;
wherein, in case the second period of time real consumption situation comprises at least one consumption object, further comprising:
determining a total number of consumption objects included in the real consumption information of the second time period;
determining a threshold based on a total number of consumption objects included in the real consumption information for the second period of time;
wherein the data analysis device is further configured to: under the condition that the consumption abnormal behavior of the target object is detected, monitoring the use dynamic state of the target object; when the target object is used again, acquiring face information of a consumer using the target object; judging whether the face information of the consumer is consistent with the face information of the user to which the target object belongs; and if the face information of the consumer is inconsistent with the face information of the user to which the target object belongs, sending a consumption abnormality reminder to the user to which the target object belongs.
6. The apparatus according to claim 5, wherein the similarity calculation unit includes:
a matching result determining unit, configured to determine, in a case where the second period of real consumption information includes at least one consumption object, a matching result of each consumption object included in the second period of real consumption information and a consumption object included in the consumption information predicted by the second period of time;
and the similarity calculation unit is used for calculating the similarity of the real consumption information of the user in the second time period and the predicted consumption information based on the matching result of each consumption object contained in the real consumption information in the second time period and the consumption object contained in the predicted consumption information in the second time period.
7. The apparatus according to claim 6, wherein the matching result determination unit includes:
the evaluation function construction unit is used for constructing an evaluation function between the consumption objects contained in the consumption information which is true in the second time period and the consumption objects contained in the consumption information which is predicted in the second time period;
and the matching result determining subunit is used for determining whether each consumption object contained in the real consumption information of the second time period is matched with the consumption object contained in the consumption information predicted by the second time period based on the evaluation function, so as to obtain a matching result.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010246737.7A CN111461866B (en) | 2020-03-31 | 2020-03-31 | Data analysis method and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010246737.7A CN111461866B (en) | 2020-03-31 | 2020-03-31 | Data analysis method and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111461866A CN111461866A (en) | 2020-07-28 |
| CN111461866B true CN111461866B (en) | 2023-09-26 |
Family
ID=71679470
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010246737.7A Active CN111461866B (en) | 2020-03-31 | 2020-03-31 | Data analysis method and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111461866B (en) |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011031886A2 (en) * | 2009-09-11 | 2011-03-17 | Visa International Service Association | System and method using predicted consumer behavior to reduce use of transaction risk analysis and transaction denials |
| CN104799518A (en) * | 2015-04-28 | 2015-07-29 | 百度在线网络技术（北京）有限公司 | Intelligent wallet as well as control method and device thereof |
| CN107679982A (en) * | 2017-09-29 | 2018-02-09 | 电子科技大学 | A kind of credit card risk checking method based on point process |
| CN107705155A (en) * | 2017-10-11 | 2018-02-16 | 北京三快在线科技有限公司 | A kind of consuming capacity Forecasting Methodology, device, electronic equipment and readable storage medium storing program for executing |
| CN109165940A (en) * | 2018-06-28 | 2019-01-08 | 阿里巴巴集团控股有限公司 | A kind of theft preventing method, device and electronic equipment |
| CN110310121A (en) * | 2019-05-24 | 2019-10-08 | 平安银行股份有限公司 | Credit card illegal use resisting control method, device, computer equipment and storage medium |
-
2020
- 2020-03-31 CN CN202010246737.7A patent/CN111461866B/en active Active
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2011031886A2 (en) * | 2009-09-11 | 2011-03-17 | Visa International Service Association | System and method using predicted consumer behavior to reduce use of transaction risk analysis and transaction denials |
| CN104799518A (en) * | 2015-04-28 | 2015-07-29 | 百度在线网络技术（北京）有限公司 | Intelligent wallet as well as control method and device thereof |
| CN107679982A (en) * | 2017-09-29 | 2018-02-09 | 电子科技大学 | A kind of credit card risk checking method based on point process |
| CN107705155A (en) * | 2017-10-11 | 2018-02-16 | 北京三快在线科技有限公司 | A kind of consuming capacity Forecasting Methodology, device, electronic equipment and readable storage medium storing program for executing |
| CN109165940A (en) * | 2018-06-28 | 2019-01-08 | 阿里巴巴集团控股有限公司 | A kind of theft preventing method, device and electronic equipment |
| CN110310121A (en) * | 2019-05-24 | 2019-10-08 | 平安银行股份有限公司 | Credit card illegal use resisting control method, device, computer equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111461866A (en) | 2020-07-28 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN116883084B (en) | Sales evaluation-based data intelligent monitoring and early warning method and system | |
| CN112200402B (en) | Risk quantification method, device and equipment based on risk portrait | |
| CN112132618A (en) | Commodity price determining method, device and equipment and readable storage medium | |
| CN109583729B (en) | Data processing method and device for platform online model | |
| CN111708883A (en) | Credit credit limit determination method and device based on machine learning and equipment fingerprint | |
| CN111179089A (en) | Money laundering transaction identification method, device and equipment | |
| CN111144899B (en) | Method and device for identifying false transaction and electronic equipment | |
| CN112232950A (en) | Loan risk assessment method and device, equipment and computer-readable storage medium | |
| US8255316B2 (en) | Integrated business decision-making system and method | |
| JP2021018466A (en) | Rule extracting apparatus, information processing apparatus, rule extracting method, and rule extracting program | |
| CN111461866B (en) | Data analysis method and device | |
| CN112884480A (en) | Method and device for constructing abnormal transaction identification model, computer equipment and medium | |
| CN110796379B (en) | Risk assessment method, device and equipment of business channel and storage medium | |
| CN108229964A (en) | Trading activity profile is built and authentication method, system, medium and equipment | |
| Mzoughia et al. | An improved customer lifetime value model based on Markov chain | |
| CN111461865B (en) | Data analysis method and device | |
| CN114707420A (en) | Credit fraud behavior identification method, device, equipment and storage medium | |
| CN112685390B (en) | Database instance management method and device and computing equipment | |
| JP2005346730A (en) | Method of determination of unauthorized utilization of credit card using history information | |
| CN114943619A (en) | Transaction abnormal account identification method, system, server and storage medium | |
| CN114298818A (en) | Risk assessment method and device for controlling goods loan | |
| CN113870020A (en) | Overdue risk control method and device | |
| CN113011748A (en) | Recommendation effect evaluation method and device, electronic equipment and readable storage medium | |
| CN116433242B (en) | Fraud detection method based on attention mechanism | |
| CN112116357B (en) | Method and device for realizing cashing detection and computer equipment |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |