Categorizing financial transactions and matching images

After a successful meetup, Cubonacci is hosting another episode of the Applied Machine Learning series, where practitioners will share machine learning use cases from ideation until production. We are excited to host two companies talking about their interesting and very different challenges.

Agenda:

18:00
Doors open, Pizza and Drinks

19:00
Welcome and Cubonacci introduction by Jan van der Vegt

19:10
Categorizing financial transactions for personal finance management at Yolt

By Alexander Backus, Lead Data Scientist at Yolt and consultant at BigData Republic

Yolt, a fintech venture of ING Bank, is continuously improving their financial transaction categorization engine to provide app users with a comprehensive overview of income and spendings. But how to approach this seemingly clear-cut classification task and what are the key considerations? In this talk, Alexander will discuss all aspects, from business requirements to algorithms, starting with a simple model and moving on to label embedding neural networks.

19:45
Break

20:00
Deep image matching

Marijn Lems (iam.io) will take you through the process of training the deep learning model that they use for image matching.

We discuss some fun and interesting challenges during data collection, hand labeling, cleaning, preparation, modelling and operationalization. Then we will dig deeper in what type of CNN architectures for image matching proved to work and how we optimized hyper parameters. We will look into deep representation learning and cover sampling procedures that boosted image matching performance.

ImageLink (a product of iam.io) replaces QR codes using image matching technology. Instead of scanning a QR code, you scan images. A new and exciting way of activating your (printed) assets.

20:35
Drinks and networking

21:30
Doors closed