State-space models capture very well the evolution of the electricity demand; in particular, they perform well in the context of abrupt regime changes. The objective of Viking Conseil is to continue to develop this state-space methodology, while comparing it to other forecasting approaches.
- Joseph de Vilmarest and Yannig Goude (2022). State-Space Models for Online Post-Covid Electricity Load Forecasting Competition. IEEE Open Access Journal of Power and Energy.
- Joseph de Vilmarest and Olivier Wintenberger (2021). Stochastic online optimization using kalman recursion. Journal of Machine Learning Research.
- David Obst, Joseph de Vilmarest and Yannig Goude (2021). Adaptive Methods for Short-Term Electricity Load Forecasting During COVID-19 Lockdown in France. IEEE Transactions on Power Systems.
- Guillaume Lambert, Bachir Hamrouche et Joseph de Vilmarest (2023). Frugal day-ahead forecasting of multiple local electricity loads by aggregating adaptive models. Nature Scientific Reports.
- Joseph de Vilmarest, Jethro Browell, Matteo Fasiolo, Yannig Goude et Olivier Wintenberger (2023). Adaptive Probabilistic Forecasting of Electricity (Net-)Load. IEEE Transactions on Power Systems.
- Joseph de Vilmarest and Olivier Wintenberger (2021). Viking: Variational Bayesian Variational Tracking.
- Joseph de Vilmarest and Olivier Wintenberger (2019). Logarithmic Regret for parameter-free Online Logistic Regression.
- February 2022 – February 2023. Participation to the M6 Financial Forecasting Competition with Nicklas Werge (team AdaGaussMC_STU), focus on the Forecasts leaderboard. Awarded 3rd place during the 1st quarter and 5th global.
- June 2021. 1st place at the Competition on building energy consumption forecasting.
- March – April 2021. 1st place with Yannig Goude at the Day-Ahead Electricity Demand Forecasting: Post-COVID Paradigm.
Viking Conseil, SAS
157 rue de l’Université, 75007 Paris
joseph.de-vilmarest [at] vikingconseil.fr