Shengsheng (Shane) Huang is a senior software architect at Intel and an Apache Spark committer and PMC member. She serves a leading role in the development of distributed analytical applications, ML/AI models, and infrastructure support on Spark at Intel (specifically, the open source projects BigDL https://github.com/intel-analytics/BigDL and Analytics-zoo https://github.com/intel-analytics/analytics-zoo. She is also the program committee of the O’Reilly AI conferences.
Time Series Forecasting is widely used in real world applications, such as network quality analysis in Telcos, log analysis for data center operations, predictive maintenance for high-value equipment, etc. Classical time series forecasting methods (such as autoregression and exponential smoothing) often involve making assumptions the underlying distribution of the data, while new machine learning methods, especially neural networks often perceive time series forecasting as a sequence modeling problem and have recently been applied to these problems with success (e.g., [1] and [2]). However, building the machine learning applications for time series forecasting can be a laborious and knowledge-intensive process. In order to provide an easy-to-use time series forecasting toolkit, we have applied Automated Machine Learning (AutoML) to time series forecasting. The toolkit is built on top of Ray (a distributed framework for emerging AI applications open-sourced by UC Berkeley RISELab), so as to automate the process of feature generation and selection, model selection and hyper-parameter tuning in a distributed fashion. In this talk we will share how we build the AutoML toolkit for time series forecasting, as well as real-world experience and 'war stories' of earlier users (such as Tencent). References:
