GiniMachine is an AI-based decision-making platform that utilizes advanced machine learning algorithms and the company’s historical data to build high-performing scoring models.
It can be used for application scoring, credit scoring, collection scoring, marketing purposes (churn prediction to create personalized offers), and sales activities (cross-selling and upselling opportunities).
GiniMachine adds value to banking, finance, telecom, and other businesses able to provide large datasets for analysis.
The system uses a custom implementation of the decision tree ensemble method strengthened with a set of heuristics for preliminary data processing and preparation.
Key benefits of the solution are:
Fast, fully autonomous, and automated model building process. With a prepared dataset, it takes only 2-10 minutes to build and validate a scoring model. Thus, it saves hundreds of hours of manual work for risk officers and data analysts.
High performance and predictive power of a model. Typically, up to 15 points of the Gini Index compared to traditional models based on logistic regression (logit).
Ease of use — no special training required to build a model.
Built-in scoring model evaluation and validation tools.
Ability to use unstructured and big data, handle imperfect and missing data, find hidden dependencies.
Proven economic efficiency — fewer NPLs, better performance of a loan portfolio, higher acceptance rate, etc.
Besides, GiniMachine is a great data analysis tool for risk managers. It provides valuable insights into lender’s data and serves perfectly well for exploratory analysis.
