Prediction Improvement on Userâs Consumption

The goal of the research is to implement different data mining algorithms in order to improve the prediction on a userâs electricity consumption. The research will be dedicated to improve the existing algorithms or implementing new algorithms for the improvement of the prediction accuracy. Besides application of the prediction algorithms, different data pre-processing methods will be used. Research will include supervised and unsupervised modelling of the dataset by using the R programming language. As well, the segmentation of the customers based on the similarity measures in order to increase the prediction accuracy will be investigated. This research will lead to the improvement of the prediction accuracy which will bring more customers to the company as well as help the existing customers to save more energy, therefore more money.

Faculty Supervisor:

Sabine McConnell

Student:

Vazgen Minasyan

Partner:

Lowfoot Inc

Discipline:

Computer science

Sector:

Energy

University:

Program: