Kishan Manani
Kishan is a machine learning and data science lead, course instructor, and open source software contributor. He has contributed to well known Python packages including statsmodels, Feature-engine, and sktime. He has 10+ years of experience in applying machine learning and statistics in finance, e-commerce, and healthcare research. He leads data science teams to deliver data and machine learning products end-to-end.
Kishan attained a PhD in Physics from Imperial College London in applied large scale time-series analysis and modelling of cardiac arrhythmias; during this time he taught and supervised undergraduates and master's students.
LinkedIn: https://www.linkedin.com/in/kishanmanani/
Medium: https://medium.com/@kish.manani
Twitter: https://twitter.com/KishManani
GitHub: https://github.com/KishManani
Sessions
Evaluating time series forecasting models for modern use cases has become incredibly challenging. This is because modern forecasting problems often involve a large number of related time series, often hierarchical, with a diverse set of characteristics such as intermittency, non-normality, and non-stationarity. In this talk we'll discuss all the tips, tricks, and pitfalls in creating model evaluation strategies and error metrics to overcome these challenges.