Energy-Demand-Time-Series-Forecast-v04 [Predictive Exp.]

December 2, 2018

Report Abuse
Business Goals: The Energy Demo goal is to demonstrate a typical predictive analytics and machine learning solution that can be deployed in a very short time frame. Specifically, my current focus is on enabling energy demand forecast solutions so that its business value can be quickly realized and leveraged upon. Using Azure Machine Learning for the implementation and deployment of Energy Forecasting Solutions scoring 97% accuracy of prediction.
The modeling process includes: 1 Data preparation to clean and format the data (for simplicity reason this step was performed in MS Excel Power Query) 2 Creating features for the machine learning models from raw time series data ([MS Excel Power Query][1]) ![PowerQueryTimeSeriesConversion][2] 3 Training machine learning model 4 Evaluating the models by comparing their performance on a held-out test dataset 5 Operationalizing the best model, making it available through a web service to generate forecasts on demand. More details and data sourses are here: [][3] [1]: [2]: http://%20%20%20%20%20%20%20%20%20Energy-Demand-Time-Series-Forecast/PowerQueryTimeSeriesConversion.jpg [3]: