We have created extraordinary value for our clients through the use of Advanced Analytics and Big Data approaches. Our work typically leads to 30-200% improvement for our clients, with our clients realizing more than 20x ROI on their investment in us. These results have been achieved across verticals – payments, consumer lending, e-commerce, retail, etc - and functional areas – digital marketing, telesales, risk & fraud management, customer engagement, churn management, etc. We have used a multitude of approaches in generating these results , such as Statistical Clustering, Regression Modeling, Lifetime Value analysis, Decision Trees, Machine Learning, A/B Testing, Association Rule design, Linear Optimization, etc.
The case studies below provide more information on projects delivered for our clients.We drove the segmentation overhaul at a leading credit card issuer, identifying behavior & profitability based segments and developing targeted strategies for each segment. The approach involved identified customer segments with differentiated profitability profiles, understanding the key behavioral differences, and then developing strategies suited to...
We led loss mitigation initiatives at a major global credit card issuer by developing a dynamic, transaction-based scoring algorithm. The goal was to reduce credit losses incurred by new card customers. The approach complemented the traditional credit bureau based approach and took into account unstructured...
We drove 60% increase in cross-sell rates for a leading e-commerce client. To achieve this, we developed a real-time customized recommendation engine that predicted the most optimal array of cross-sell products to be shown to a visitor. The engine was based on the contents of...
We simplified the credit approval process for a major global bank by developing a credit policy based on traditional & non-traditional data. The central pillar of the approach was an ensemble model that predicted an applicant’s income, using traditional credit bureau data, along with alternative...
We helped a major US payments network reduce fraudulent transactions by developing a customized fraud prediction algorithm. The approach involved combining structured and unstructured data from a variety of sources – including Retail PoS data, ATM & other transaction data, geographic information, and historical cardmember...
We used sophisticated testing and optimization techniques to overhaul the online marketing program of a global pharmaceutical leader. This initiative involved performing rigorous testing on keywords, bids, & ad positions and then building predictive algorithms & optimization models to refine the allocation of the SEM...
We assisted a major e-commerce firm in expanding to the telesales channel. In order to make this economically viable, we developed a prospect response model that predicted the probability of phone conversion. This statistical model took into account the past behaviors of customers, including purchase...
We drove email customization efforts for a major e-commerce player. For this, we developed an algorithm that inferred customers’ interests based on past purchases, email behaviors, site visit information, and demographics. The content of the email was then automatically modified to suit each individual’s interests....
We drove significant cost reductions for one of America’s largest media agencies through the use of analytics in display advertising. The initiative involved using clickstream data collected on millions of web users who were exposed to the client’s display ads. We undertook a massive data-crunching...
We drove an overhaul of card activation strategies for a major credit card issuer, with the goal of increasing first-time activations. This was achieved through a two step workstream – (a) identifying early predictors of long-term activity, and (b) designing, testing, and refining targeted strategies...
We used machine learning models to drive 25% increase in credit card applications Approach Client was a US credit card issuer, acquiring customers through Direct Mail and Digital channels We optimized DM strategy by first developing a “Cold Start” response prediction model (for the initial...
Our credit risk model used machine learning & regression variants to reduce losses by 10% Approach Client was a large global bank Indus re-developed the application stage risk model for Client’s Personal Loans business, followed by credit policy redesign Indus tested various scorecards, horseraced multiple...
We developed application level credit card LTV model for a leading bank and used LTV model to overhaul decision & line policy and evaluate new products Approach Client was a large global bank w/ ~6 Million card customers Indus was tasked with overhauling valuations of...
We helped a major US payments network reduce fraudulent transactions by developing a customized fraud prediction algorithm. The approach involved combining structured and unstructured data from a variety of sources – including Retail PoS data, ATM & other transaction data, geographic information, and historical cardmember...
We have driven 35% loss savings through optimization of the early collections process Approach Client was a major global bank Indus was tasked with optimizing early collections strategies of the personal loans business Identified an exhaustive list of collections outcomes; Used to streamline the collections...
