This was the final project for my Machine Learning (II) class at Ecole Polytechnique (MSc Data Science, 2019-2020).
The goal was to train an algorithm to replace usual house energy consumption monitoring systems which are too intrusive and too expensive. This challenge is known as NILM (Nonintrusive load monitoring) or NIALM (Nonintrusive appliance load monitoring). The aim of the challenge was to predict the proportion of electric consumption in one household dedicated to 4 appliances (washing machine, fridge_freezer, TV, kettle) based on time data.
This challenge was provided by ENS (Ecole Nationale Supérieure): https://challengedata.ens.fr/participants/challenges/29/.
We used regression models, detailed in our report here.