FinML — Machine Learning with Digital Behavioural Data

In this week’s meetup Apoorv and Charmee walked us through their thoughts of what digital data is and how to use it for ML applications!

Key takeaways from the talk:

• Every interaction a visitor/customer has leaves a pretty big digital footprint and it is very useful to tap into that footprint
• When building a model from such high velocity and high volume data, it is useful to use a lookback/lookahead framework for data preparation as that not only simplifies data preparation but also makes it easy to continuously monitor model performance once a model is productionized
• Laying the groundwork of connecting your ML results to actionable endpoints like onsite experience, email, advertising is very useful in driving the maximum benefit from your models
• Look for ways to reuse your models across all endpoints to compound business benefits from a single model

On FinML

FinML is a meetup group dedicated to applications of Machine Learning in finance. We are a group that is dedicated to discuss the economic and statistical concepts behind running Machine Learning in the real world. We strongly believe in discourse, which is why our sessions are 30 min presentation and 30 min open discussion. Sign up here to be invited to all of our meetups and contact myself in case you are interested in speaking at an event!