Selected Presentations & Appearances
Customers today receive personalized recommendations across several domains including e-commerce, entertainment, and travel. This degree of customization, however, is still nascent in the financial industry with the current standard being heavily reliant on user surveys. With the power of Insights Engine, financial industry can harness the treasure of transaction data to create highly personalized, conversion focused customer engagement. Insights Engine leverage transactions enhanced by algorithms based on lookalike modeling, BNP techniques and temporal clustering to generate customized insights. The Insights Engine generates comprehensive, temporally evolving, and granular trends based entirely on the transactions in the account. Sample attributes for trends can include financial behavioral preferences in spending habits, lending, and cash flow predictions that enable personalized and actionable recommendations for Financial Service Providers (FSP) and account holders. IE can drive data-driven personalization needed for consumers to find and access tools in for their financial wellness. In this talk, we will explore how the Insights Engine provides timely recommendations, reduces costs to democratize access to financial products for all users. We will also dive into the comprehensive tech stack that powers IE, leveraging over than a dozen deep learning algorithms to process 80 million+ transactions daily, generate real-time insights, and make them easily consumable for clients to be utilized into apps, banking portals or existing customer engagement tools.
Session Abstract: Deploying data science into production is a big challenge. With the rapidly changing available data sources, types, and the methods available for their analysis, there is a continuous need to update deployed data science models frequently. This makes it difficult to count on agreed –upon standards and design or work within the framework of exclusive tools. Envestnet | Yodlee delivers financial insights using transaction data to millions of users every day. Our ‘Transaction Data Enrichment’ solution turns ambiguous transaction information into clear, contextualized data using sophisticated artificial intelligence and machine learning to achieve industry-leading accuracy across a wide range of account and transaction types. This talk is not just about our journey towards successfully productionizing such a data science solution, but also about sharing our learnings and some best practices we have built over the years working with massive volume and ever changing schema of data. In this session, we will discuss the steps for building deployment ready data science solutions – from problem formulation, strategies for ground truth creation, etc. to model deployment, monitoring, maintenance and updates. We will also understand why measuring quality is a critical trade-off call in data science.