The paper introduces LOBERT, a general-purpose encoder-only foundation model designed for financial Limit Order Book (LOB) data. It adapts the BERT architecture by treating entire multi-dimensional LOB messages as single tokens, preserving continuous price, volume, and time representations. LOBERT outperforms prior models in tasks like mid-price movement prediction and next-message forecasting while requiring shorter context lengths.
arXiv:2608. 13082v1 Announce Type: cross Abstract: Generative models of limit orderbook (LOB) data have advanced rapidly, but their evaluation often focuses on stylised facts and selected market statistics.
DualCast is a dual‑path language model that forecasts financial time‑series by combining a fast numerical forecaster with an optional text‑conditioned revision mechanism. The fast path trains only new financial‑token embeddings and output heads on a frozen Qwen3‑8B backbone, while the slow path uses a LoRA adapter to incorporate news and refine predictions. In zero‑shot tests across equities and energy prices at multiple time resolutions, the slow path achieves the lowest mean absolute percentage error in most settings, especially for longer horizons, and news ablations show additional gains in many markets.
arXiv:2606. 29347v1 Announce Type: cross Abstract: Adaptive Financial Transformer (AFT) is proposed for stock return prediction under non-stationary financial markets.
The paper introduces Temporal Kolmogorov‑Arnold Networks (T‑KAN) for forecasting high‑frequency limit order book data, replacing fixed linear weights in LSTMs with learnable B‑spline activation functions. This approach captures the shape of market signals, yielding a 19.1% relative improvement in F1‑score at a 100‑step horizon and a 132.48% return versus a -82.76% drawdown for DeepLOB under 1.0 bps transaction costs. T‑KAN also offers interpretability through visible dead‑zones in the splines and is optimized for low‑latency FPGA deployment via High‑Level Synthesis.
arXiv:2607. 13929v1 Announce Type: new Abstract: Financial observations are continuous, heterogeneous, and noisy, whereas decoder-only next-token models are usually built around discrete symbolic inputs.
META (Memory Enhanced Trading Agent) is a new agent-based trading framework that augments large language models with episodic memory. It combines specialized indicator agents—such as Trend, MACD, Stochastic, RSI, SMA, AVWAP, and Heikin‑Ashi—with a Decision Agent that fuses their reports, while a Memory module retrieves and updates past trading episodes encoded as market state embeddings with outcomes and reflections. By recalling relevant experiences and adaptively reweighting signals under similar market regimes, META improves directional accuracy and robustness in short‑horizon evaluations, offering regime‑aware, interpretable, and low‑latency decision‑making for financial trading.
VertiFuseX is a hybrid LSTM architecture that fuses multi‑scale temporal representations at the penultimate layer, stacking features from LSTM, Bi‑LSTM, and St‑LSTM branches and a parallel DNN stream. On 15 years of global equity index data, it reduces MAPE by 30‑54% and improves MAE and RMSE by over 40% compared to LSTM baselines, outperforming seven state‑of‑the‑art models across 33 metric‑dataset comparisons. The model is lightweight (675k parameters, 2.6 MB footprint) with 1.5 ms/sample inference latency and demonstrates robust, interpretable forecasting with reduced drawdowns in algorithmic trading simulations.
Deep Limit Order Book forecasting models capture nonlinear market dynamics, but their ability to quantify the effects of counterfactual order book messages has not been systematically validated. We in...
The paper introduces PRICE, a systematic framework for adapting Large Language Models to short‑term Bitcoin price forecasting. PRICE combines parameter‑efficient fine‑tuning with LoRA, recursive multi‑step inference, integer‑rounded numerical representation, Context‑Task‑Format prompting, and exact zero‑temperature decoding, all built on a 4‑bit quantized LLaMA‑3 8B model. Ablation studies and comparative evaluations show that each component improves accuracy and reliability, enabling PRICE to achieve the lowest forecasting errors among eight transformer‑based and time‑series foundation models.
Predicting extreme price movements in high-frequency financial markets is a challenging task due to non-stationarity, heavy-tailed return distributions, and severe class imbalance. In particular, rare but impactful events are often difficult to detect using conventional modeling approaches, which typically treat extreme movements as isolated observations.
The paper demonstrates that deep limit order book forecasting models can be repurposed to quantify scenario-conditioned market impact without retraining. By injecting counterfactual order‑book messages into a trained Transformer forecaster, the authors compare predictive distributions before and after the injection, defining a short‑horizon model‑implied market impact. The approach achieves a Spearman correlation of 0.99 and 97.2% directional agreement with historical outcomes for non‑neutral scenarios, and captures incremental sequence‑dependent variation beyond scenario identity and pre‑event forecasts.
arXiv:2607. 17555v1 Announce Type: new Abstract: Predicting extreme price movements in high-frequency financial markets is a challenging task due to non-stationarity, heavy-tailed return distributions, and severe class imbalance.