Episode Title : Data Strategy for FinTech use cases such as Fraud Detection
Episode Summary: Artificial Intelligence and Machine Learning (AIML) has been extremely beneficial for some use cases such as fraud detection in FinTech sector. AIML enabled companies to do real-time fraud detection from what used to be a batch-oriented fraud detection. But to be able to do that, companies need to have an enterprise wide data platform. Additionally, organizations need to think through the entire process of AIML instrumentation to adopt to changing use cases and not just data and models. Lastly, COVID focused businesses to compress technology adoption to a few months and this has been good for businesses.
Collaboration on ‘AI – The Book’ (04:33): This team in UK came up with the concept of a crowdsourced book about AI. They requested initial drafts from experts in FinTech world and they selected the final authors. Each author wrote one section of the book for a completely crowdsourced book. Both Peggy Tsai and Shailendra Malik contributed to the book and are co-authors along with others.
Fraud detection using AIML (09:48): Prior to AIML, banks could only select a sample of transactions to detect fraud and that too at the end of the day or so. With AIML, banks are now able to detect for anomalies in real-time at least for known fraud schemes. For newer types of frauds where the models are not trained yet, the models still need to get trained after the fact. Still, we are way ahead from where we were few years ago.
Data, modeling, and instrumentation (15:30): Typically companies identify a use case, build models, train the data, deploy in production and consider done. What if the use case changes? How can you re-instrument the entire model and training data etc? To avoid this ongoing technical debt, there are newer frameworks where the entire process/model can be containerized into a framework.
Data wrangling, data preparation for AIML (24:07): Putting together an enterprise data platform is absolutely essential for any AIML work. DBS was proactive in establishing this model. Without those guidelines that are somewhat customizable for each of the departments, implementation of modern technologies will not take off. A platform approach for consumer banking, investment banking etc. will be very helpful.
COVID impact on FinTech (27:07): COVID has compressed the technology timeframe from multiple years to a few months. This has been very beneficial for many companies. Because of this the financial industry will go through a quantum leap in the next few years.
Resources mentioned in this episode:
DBS Bank https://www.dbs.com
Agility Exchange blogging Platform: https://agilityexchange.com/
Data Transformers Podcast
Join Peggy and Ramesh as they explore the exciting world of Data Management, Data Analytics, Data Governance, Data Privacy, Data Security, Artificial Intelligence, Cloud Computing, Internet Of Things.
