Description
PyData Berlin 2016
Harnessing the power of machine intelligence to empower users with advanced and smarter banking solutions.
Banking has been the one of the most ancient professions for humans. Yet, when it comes to advanced or smart banking solutions we haven’t experienced a radical shift even in the 21st century.
We, at Number26, aim to enrich that experience and provide an advanced, mobile banking platform for our customers. Each of our features, revolves around users - their interests and personal preferences. We achieve such flexibility by the use of state-of-the-art machine learning and statistical learning methodologies.
In particular, we would like to present a deeper insight into two major features we use in our product:
- automatic real time categorisation of transactions: how we combine the power of the cloud computing service (AWS), with the intelligence of machine learning based models to achieve this
- predictive modelling of users future financial status: how artificial neural networks do the smart thinking for our users to come up his predicted personal finances.
The tech stack ranges from Python (Keras, scikit-learn and more), Dockers, AWS lambda, EBS, NLP (stanford nltk) and machine learning classifiers and more.
In this presentation, we would like to make the message clear, how machine learning can make even the age old traditional ways of banking a fun.