Machine Learning techniques are widely adopted in the financial domain through many applications ranging from automated fraud detection, stock market prediction, delinquency prediction, global market understanding to financial document analysis. Despite advances of AI and its adoption in these areas over the years, the current pandemic has exposed challenges of handling such uncertainty in each one of these application areas. Several studies have reported that global payment fraud rate has increased since the pandemic, and so have the different ways of doing fraud. Similarly, credit risk models have been challenged and so have been other applications in the financial domain.

It is not surprising that AI applications in the financial world are often the most affected by such an uncertainty. Broadly, uncertainty can often be attributed to either (i) data uncertainty or (ii) environmental uncertainty. While modelling in the Financial world often suffers from data uncertainty due to noisy samples, limited variability, seasonality, etc., the financial world is also marred by environmental uncertainty such as pandemics and recession periods. This workshop thus provides a platform for experts across industry and academia to discuss and present challenges, novel solutions, and pave the way for future directions in modelling sequential data uncertainty for the financial world.

We invite papers focused on modelling sequential data uncertainty for financial applications. Topics of interest include, but are not limited to the following:

Application Topics:

- Evaluating financial risk
- Forecasting stock market
- Modelling seasonality in market trends
- Fraud prediction
- Modelling temporal social media activity
- Recommendation systems

Technical Topics:

- Temporal/Sequential data modelling – clustering, classification
- Modelling uncertainty in financial data
- Temporal graphs
- Time Series Forecasting
- Text analytics of financial reports, forecasts, and documents
- Explainable/interpretable sequential modelling
- Exploring fairness and robustness towards bias in financial models
- Representation learning from temporal/sequential data
- Modelling financial data as temporal point processes