Success Story - en

Retail customer profiling

Description: the high conversion rate of Bank product offers to Bank customers implies a deep understanding and analysis of the Bank's customer behavior, while information about customer spending on Bank cards is a valuable source of user data. Thematic modeling and customer segmentation is performed by decomposing the initial customer transactions into interpreted behavior profiles, and then selecting the most attractive customer groups for further product sales.

Context: it is necessary to personalize content and offers, and for this purpose it is possible to use information about the user's interaction with the system.

Decision: a hierarchical temporal model of soft client clustering is constructed.

Results:
The pilot project was conducted and integrated into the customer's business process:
Identified topics 80% of bank card users;
85% of consumption profiles are interpreted;
Predicting socio-demographic parameters of the audience;
A two-level hierarchy of customer consumption profiles is constructed;
Solved the problem of searching for similar consumers "Look-a-like".

To build the model, we used:
Bank customer transactions;
Description of MSS codes and merchants;
Accompanying information about the user;
Results of sales of banking products.

Simulation result:
Model the behavior of users of the Bank;
Probability prediction model before purchasing a banking product;
Segments of the client base.

Customer: Finance, Banking

Technology stack: TopicNet, BigARTM, gensim, Python
Natural Language Processing Personalization