Language change icon for desktop
English  |  Dutch  |  French
/ /


Customer Insights


One business challenge that financial services institutions focused on lending face is the risk of default on a mortgage. Firms can address this challenge today by using the customer’s transaction data from income, spend, social and online behavior to predict the probability of him/her defaulting based on the forecast of his spend, income and stability with respect to his/her peer group.

Synechron’s Data Science solution for Customer Insights allows banks to bring together their Know Your Customer (KYC), Banking, and Credit Card Data into a database, and join them with the customers online behavior (customer has to opt in) via web and social platforms. The mortgage, credit card and banking modules can use this data to inform a custom profile, display and predict transaction patterns, identify peer groups for active products design, find customers influence and impact within their networks, identify anomalies and risks/risk areas and generate analytics around a customer for a more productive, data-drive conversation.

Synechron’s Data Science solution for Customer Insights has four Modules for Banks, Credit Cards, e-Commerce and Mortgages – each module having a separate user interface and communicates across secure web services.

Synechron uses powerful Data Science technologies to deliver solutions that analyze structured and unstructured data to answer business questions related to customers, products and threats. The Data Science solutions allows financial services firms to:

  • Customer Clustering in peer groups based on independent/collective parameters to design financial products suitable for the groups
  • Customer Transactions Analysis and prediction based on history, peer groups and online changes
  • Customer Risk Profiling - transaction anomaly detection for corrective actions/recommendation
  • Customer Rules Engine – Historical customer transaction data undergoes time series analysis where income and spend trends are calculated seasonally, clustering customers based on their income / spend / location / marital status etc.
  • Cookie Matching - Dummy webpages and custom tracking tags are used to reveal customer browsing behavior
  • Social Integration – Pulls in data from Twitter and analyzing it using NLP to find out the category, topic and sentiment of the feed posted by the user
  • Technology specifications - Java / J2EE, Spring, restful web services, HTML5, Angular JS, MySQL database, R, Python, NLTK, Neuroph, Encog, Deeplearning4j

To learn more about our Artificial Intelligence solutions for Data Science and the work we’re doing email us at