TailDART: Compute-Efficient Foundation Models for Financial Time-Series Forecasting
Organizations: Nanyang Technological University Singapore · Agency for Science, Technology and Research Singapore
Abstract
Although time-series foundation models (TSFMs) achieve strong zero-shot transferability across high-information-density physical systems, applying overparameterized TSFMs to quantitative finance is fundamentally constrained by low signal-to-noise ratios, non-stationarity, and prohibitive autoregressive decoding latency. To reconcile representation learning with institutional operational constraints, this study presents TailDART, a dense 2.68 million-parameter foundation model engineered for financial time-series forecasting. By integrating grouped-query attention into a lightweight backbone, the architecture drastically reduces Key-Value cache memory bandwidth overhead, achieving major inference acceleration (up to 48.1%) over prevailing state-of-the-art TSFMs to enable low-latency, high-throughput streaming execution. Furthermore, multi-asset benchmarks across varying temporal resolutions show that a compact model can remain competitive for market forecasting: TailDART matches the predictive fidelity of substantially larger baselines while demonstrating superior error resilience in high-volatility regimes.
Figures & tables
| Source/group | Dataset names |
| ETT | ETTh1 , ETTh2 , ETTm1 , ETTm2 |
| GluonTS electricity/energy | australian_electricity_demand , electricity_hourly , london_smart_meters_without_missing , solar_10_minutes , wind_farms_without_missing |
| GluonTS transport/mobility | pedestrian_counts , uber_tlc_hourly , traffic , traffic_nips |
| GluonTS weather/environment | kdd_cup_2018_without_missing , saugeenday , sunspot_without_missing , weather |
| GluonTS exchange rates | exchange_rate |
| GluonTS M4 | m4_daily , m4_weekly , m4_monthly |
| Daily | Weekly | Monthly | ||||||||
| Model | Params (M) | MASE | RMSE | Latency (ms) | MASE | RMSE | Latency (ms) | MASE | RMSE | Latency (ms) |
| TailDART (Dense) | 2.68 | 0.859 | 0.0201 | 0.668 | 0.899 | 0.0411 | 0.689 | 0.842 | 0.0977 | 0.912 |
| TailDART (MoE) | 2.68 | 0.865 | 0.0204 | 1.058 | 0.908 | 0.0421 | 1.094 | 0.848 | 0.0995 | 1.629 |
| Lag-Llama | 2.45 | 0.854 | 0.0204 | 1.288 | 0.906 | 0.0423 | 0.986 | 0.855 | 0.1002 | 1.234 |
| Chronos-T5-tiny | 8.39 | 0.819 | 0.0191 | 1.047 | 0.857 | 0.0384 | 0.704 | 0.821 | 0.0931 | 1.021 |
| Sundial-base | 128.00 | 0.798 | 0.0185 | 7.019 | 0.846 | 0.0385 | 6.907 | 0.802 | 0.0929 | 8.042 |
| MASE | RMSE | ||||||
| Asset group | TailDART | Lag-Llama | TailDART | Lag-Llama | |||
| Daily | FX | 0.827 | 0.823 | +0.5% | 0.0060 | 0.0058 | +2.4% |
| EM FX | 0.847 | 0.819 | +3.3% | 0.0047 | 0.0044 | +7.0% | |
| MSCI | 0.864 | 0.869 | -0.5% | 0.0164 | 0.0165 | -0.4% | |
| Rates | 0.847 | 0.839 | +1.0% | 0.0246 | 0.0243 | +1.3% | |
| REITs | 0.955 | 0.931 | +2.6% | 0.0258 | 0.0227 | +13.4% | |
Time Series Forecasting
Time series forecasting predicts future values from ordered observations using statistical, neural, and probabilistic models to support decisions under uncertainty.
See all 939 papers