Omar Abdesslem

Power Grid Load Forecasting using Machine Learning

A data-driven thesis modeling Swiss electricity load using Time Series and Machine Learning. Forecasts were informed by seasonality and enriched with exogenous weather data. The project applied rigorous time series diagnostics and evaluation metrics.

Predicting Box Office Success: Analyzing Film Industry Data

With friends, I Participated in the TMDB Box Office Prediction Big Data competition on Kaggle.

Our goal was to use Machine Learning to predict a film's sucess based on the movie's metadata from imdb.

Various models were tried, and the best fitting model was selected based on performance.

Final root mean squared logarithmic error was 1.9 (unitless), top 30% among 1,400+ global submissions

SwissGrid: Prediction of PV installation angles

Winner team for the Swissgrid Challenge for Energy Data Hackdays, Aargau.

For this project, we used Databricks and Python to predict photovoltaic (PV) installation angles (orientation and tilt) for over 233,000 PV plants in Switzerland.

Our predictive models estimated installation angles to fill in missing data, enhancing forecast accuracy for renewable energy generation. Through this project, we gained experience in geospatial data clustering, handling big data with Databricks, and applying predictive modeling for energy forecasting.