Quantitative Analytics helps businesses use their own data to better understand their customers based on behavioral patterns expressed through interactions with the provider over a period of time. This informs our work in advising providers on how to serve their customers better through improved products, over a variety of channels, and targeted to appropriate sub-segments.
We leverage a suite of proprietary analytical modules that combine traditional statistical analysis, machine learning, and data visualization that is capable of handling large volumes of unstructured financial data.
Quantitative Analytics is highly specialized for the following purposes:
- We mine billions of transactions pertaining to millions of customers over many years using applied statistics, segmentation, clustering, machine learning, natural language processing etc. Data sources include banks, other financial institutions, utilities, digital financial service providers, and even informal savings and credit groups. This allows us to very precisely understand customer preferences based on their actual usage behavior.
- We utilize various statistical and machine learning based modeling techniques to make predictions based on descriptive and historical data. This includes credit scoring, propensity for cross-sell, future portfolio performance and the financial impact of business decisions as some examples.
- We triangulate evidence with other practice areas in BFA to obtain a holistic image of a customer or a provider. For example, behavioral pattern discovery informs Customer Insights on preferred customer behaviors, while transactional segmentation allows the Business Insights team understands the financial performance of products, channels, and customer segments.