WARA AI TRICS: Time Series Challenge

WARA AI-TRICS brings real-world time series challenges from industry to the academic community. The first WARA AI-TRICS Open Challenge invites participants in Sweden to develop innovative solutions to problems in finance, telecommunications, and industrial systems.
The challenge aims to encourage new research approaches, strengthen collaboration between academia and industry, and build a research community around time series. The ambition is to make it an annual event, introducing new problems and industry partners each year.
Who can participate
Participating teams, with a recommended size of 4 to 6 people, are encouraged to register their team as soon as possible, to help secure access to compute resources.
Following strong interest in the challenge, participation has been expanded to welcome more members of the academic community
The SEB and Ericsson challenges are open to:
- PhD students and postdoctoral researchers within and outside WASP
- Other university students in Sweden
- University faculty members in Sweden
The IPercept challenge is open to PhD students and postdoctoral researchers within WASP.
WARA AI-TRICS provides computational infrastructure and resources for participating teams, with priority given to WASP students.
The three challenges
Traditional time series forecasting models often operate primarily on the historical observations of a target signal. However, in complex real-world dynamics, a single time series rarely contains enough information to explain all structural shifts, tail events, or localized anomalies. A sudden deviation, peak, or drop in a target signal is frequently driven by underlying contextual regimes, interactions with related signals, or external multimodal information.
To demonstrate the applicability and generality of this paradigm, participants will tackle solutions across three distinct, real-world domain case studies:
- Quantitative Finance (SEB): Modeling structural asset price deviations using an auxiliary regime variates dataset containing macroeconomics, rates, and volatility signals.
Contact: Alireza Javid (alireza.javid@seb.se) - Telecom Systems (Ericsson): Forecasting critical network Key Performance Indicator (KPI) behavior by capturing spatial, temporal, and contextual interactions across neighboring cells, concurrent KPIs, alarms, logs, and topology.
Contact: Hannes Larsson (hannes.larsson@ericsson.com) - Industrial Machines Monitoring (IPercept): Anomaly detection in repetitive industrial robot motion using time series foundation models. A robotic system executes a structured motion pattern under controlled, repeatable conditions. Participants build models that learn normal motion from a large unlabeled corpus and detect mechanical degradation patterns in a held-out evaluation window.
Contact: Peter Troll (peter@ipercept.io)
From challenge to research publication
The best-performing teams and participants with particularly novel ideas will be invited to contribute, providing a recurring opportunity to turn challenge work into research publications and establish a citable research contribution. This challenge is open to all PhD and postdoctoral researchers in Sweden, with computational infrastructure and compute resources provided by WARA AI-TRICS.
Registration and important dates
Registration: We recommend to register your team as soon as possible to help secure access to computational resources. Registration remains open until submission deadline.
Submission: Teams who are registered above must submit their solutions by February 28, 2027, 23:59 CET.
Further information on cloud compute access, and submission portal will be announced here.