The financial industry is dealing with record amounts of data flowing faster than ever, so smarter analytics will increasingly become the competitive differentiator among financial institutions. The true strategic value of these data streams is to predict consequential outcomes at critical decision points, optimizing operational decisions in core processes.
Credit risk and marketing response models will remain critically important for acquiring new customers, but marketing analytics can also drive customer satisfaction, retention, and profitability. Consider predicting the profitability of a prospective customer owning a product before the product is offered, or knowing which person most needs their support call expedited.
Faced with the challenges of how to contain costs, increase revenue, and mitigate risks, innovative financial analytics solutions are being used to improve regulatory compliance, automate business processes, and enhance customer experience. Such capabilities are enabled by analyzing structured data and unstructured text within the data stores available to the banking and financial institutions. When expert analytics consulting expertise is combined with internal organization commitment, the strategic value of data is greatly enhanced.
Marketing analytics provides a sustainable competitive advantage by helping to understand customer sentiment and behavior and to adapt to changing customer needs. Personalizing the customer banking experience through targeted products and services improves customer loyalty and satisfaction.
Elder Research analytics consulting services can provide support throughout the journey — from assessing analytic strategy to managing the institutional challenges of integrating analytics into operational financial systems and banking processes. Making analytic insight accessible to the right people at the right time is critical to maximizing value derived from data.
Our clients—whether newly formed analytics teams or established pros—find that we help them understand their data, strengthen their teams’ abilities, and bring to the forefront basic and advanced levels of insights aligned to their needs. Examples of our banking and financial analytics solutions include:
Improving the Effectiveness of Marketing Campaigns for Financial Products
Elder Research built cross-sell and next-most-likely marketing analytics models for financial products campaigns. The models identified customer/product pairs for mass-market campaigns, as well as more rare and profitable “contact” sales opportunities. To achieve the necessary analytic breakthroughs, Elder Research developed a custom association rules software product called QuiltMaker that has since been generalized to address problems in multiple industries.
Improving Credit Card Risk Scoring
Elder Research was brought in to provide an outside perspective to enhance the credit risk scoring results for a client with an in-house team of hundreds of analysts with advanced degrees. Over many years that team had honed models to world-class levels of performance. Astonishingly, Elder Research’s expertise with a dozen modern data science algorithms was able to significantly improve the prediction of bad credit risks over the client’s models. The improved the early identification of credit card accounts likely to default led to tens of millions of dollars of annual gains for the client.
Identifying Risks in Brokerage Firm Applications
Elder Research designed and implemented sequence matching patterns for a regulatory agency to identify risks in brokerage firm compliance, anti-money laundering, and equity trading and market making applications. These technologies were incorporated into a product that operates on large data marts to uncover patterns of suspicious behavior and provide actionable alerts to financial institutions.
Predicting Financial Account Churn
Elder Research partnered with a diversified bank to predict account closures (churn), prioritize marketing interventions, and understand precursors to customer churn. The goal was to improve the predictive performance
of an existing account churn model that was based on heuristics in order to reduce account churn rates by at least 10% using only internal data. We built a predictive model that was 20% more effective at predicting customer churn than the existing techniques.