Modeling and Analytical Methods

Our modeling and analytics methods consist of:

Principal Component Analysis

This combines multiple explanatory variables into a representative few for better understanding underlying phenomena, i.e. Exploratory analysis of data sets. The principal use cases include:




Correlation Analysis

Here, we identify linear inter-relationships among variables during exploratory analysis. This is useful for producing pricing analytics




Association Rule Mining

This finds close relationships between two sets of occurrences/events (identify market-basket), and is used for cross-sell/up-sell of products


K-means clustering

Here we segment based on transaction behaviour or similarity of customer attributes, and works for Product Pricing Analytics and portfolio insights

Logistic & Linear regression

This is a generalized linear model for classification of events used in Product pricing analytics, Credit scoring, Bad Debt prediction, churn analysis

Classification and Regression Trees

A classifier which builds a decision tree based on historic examples basis which new cases can be predicted. This can be used for customer response to dunning actions and Churn Prediction

Error Msg
Error Msg
Error Msg

Questions?

  • For any risk solution related queries, please contact:
    +91 22 33428266
    Sales.Birs@crisil.com