This project is one of the Scrum projects with industry partners that were part of the AMOS Winter 2025/26 Projects. Below please find the video (you may also like the other videos) and the project summary which details the final result of the project. We run these projects every semester, so please be in touch if you would like to motivate one of your own!
Demo Video
Project Summary
| Project name | RTDIP Time Series Forecasting |
| Project mission | To design, develop, and contribute open-source forecasting components for the RTDIP platform that enable trend analysis, anomaly detection, and predictive modeling on time series data. Our mission within this project is to research and implement forecasting techniques using Python and Apache Spark, validate and enrich them with real-world datasets, and ensure they meet RTDIP’s modular, tested, and well-documented standards. By doing so, we will enhance RTDIP’s functionality and provide the open-source community and industry users such as Shell with reliable, scalable forecasting capabilities that integrate seamlessly into existing data pipelines. |
| Industry partner | Shell |
| Team logo |  |
| Project summary | The project resulted in an end-to-end time series solution. Four forecasting models were implemented and compared, alongside statistical anomaly detection to identify irregular patterns. Time series decomposition was added to extract trend and seasonality, supported by new preprocessing functionalities and integrated visualizations for efficient analysis and validation. |
| Project illustration |  |
| Team photo |  |
| Project repository | https://github.com/amosproj/amos2025ws03-rtdip-timeseries-forecasting |