FAR-Trans: An Investment Dataset for Financial Asset Recommendation
Javier Sanz-Cruzado, Nikolaos Droukas, Richard McCreadie
TL;DR
FAR-Trans addresses the lack of public benchmarks for financial asset recommendation by releasing a comprehensive dataset that combines pricing time-series, asset metadata, anonymized customer profiles, and transaction logs from a large European institution, covering 2018–2022. It enables evaluation of 11 FAR algorithms across 61 time points using $ROI@6$ months and $nDCG@10$ metrics, illustrating how price-based approaches excel at profitability while transaction-based methods better predict customer investments. The study shows that non-personalized profitability models can surpass market returns, whereas collaborative filtering approaches best capture user-specific interests, underscoring the value of hybrid strategies depending on the evaluation objective. Overall, FAR-Trans provides a practical, realistic resource for developing and benchmarking FAR methods and paves the way for portfolio optimization and investor modeling research in finance.
Abstract
Financial asset recommendation (FAR) is a sub-domain of recommender systems which identifies useful financial securities for investors, with the expectation that they will invest capital on the recommended assets. FAR solutions analyse and learn from multiple data sources, including time series pricing data, customer profile information and expectations, as well as past investments. However, most models have been developed over proprietary datasets, making a comparison over a common benchmark impossible. In this paper, we aim to solve this problem by introducing FAR-Trans, the first public dataset for FAR, containing pricing information and retail investor transactions acquired from a large European financial institution. We also provide a bench-marking comparison between eleven FAR algorithms over the data for use as future baselines. The dataset can be downloaded from https://doi.org/10.5525/gla.researchdata.1658 .