Jumping to the startup world more than 2 years ago was for me something totally new, challenging and honestly a bit scary in the beginning.
During those 2 years of building the company from scratch, we experienced many ups and downs at SimpleFinance, from pivoting the product vision, changing completely the codebase with new data providers to crafting the state of the art ML engine in property valuation used for speeding up and refining mortgage experience on US market.
It was a rush with many lessons learned. So it's time to share. In this talk, I'd like to cherry-pick a few interesting problems we faced with our data, I will mention ideas over the modelling approach, hyperparameter optimization, and confidence evaluation, discuss a few examples of how tight research setup and production should be and also give you a few tips on how to balance fast research exploration with stable continuous development...
Adam is a chief data scientist at SimpleFinance - Silicon Valley based startup revolutionizing mortgage industry using machine learning. In the past, Adam worked as researched at Seznam, improving the relevancy of web search as well as transforming image search to modern deep learning version. Adam has also experience from GoodAI and the work on AGI, he established Brno ML meetups back in 2017 and nowadays prepare lectures for people from industry about image processing with neural networks via MLCollege project.
- Networking (ImpactHub)
Machine Learning Meetups (MLMU) is an independent platform for people interested in Machine Learning, Information Retrieval, Natural Language Processing, Computer Vision, Pattern Recognition, Data Journalism, Artificial Intelligence, Agent Systems and all the related topics. MLMU is a regular community meeting usually consisting of a talk, a discussion and subsequent networking. Except of Prague, MLMU also spread to Brno, Bratislava and Košice.