OpenTox Virtual Conference 2020 Session 10: Data Science and AI Applications

Time Series Forecasting  

Time series forecasting is an important area of machine learning that is often neglected. The topic  is relevant nowadays because there are so many prediction problems that involve a time  component. These problems are neglected because it is this time component that makes time series  problems more difficult to handle. The skill of a time series forecasting model is determined by its  performance at predicting the future. This is often at the expense of being able to explain why a  specific prediction was made, confidence intervals and even better understanding the underlying  causes behind the problem. The talk will focus on various time series forecasting techniques. The  audience will gain an in depth understanding of various time series models, components of a time  series, ways to handle stationarity, and the prediction techniques. Further, the introduction of  ensemble modelling for predictive accuracy enhancement may be discussed.