Nabeel Ahmad Saidd

Mr. Nabeel Ahmad Saidd

Dr. A.P.J. Abdul Kalam Technical University, Lucknow, India
orcid
Robe

Research Focus & Metrics

Academic Career Length

1Year (2026-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 August 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
Nabeel Ahmad SaiddNabeel Ahmad Saidd
Nabeel Ahmad Saidd
Financial time-series forecasting is commonly optimized using mean-squared error (MSE), though financial returns exhibit volatility clustering, heavy tails, and regime shifts that often make a fixed quadratic objective ill-suited. We propose Regime-Normalized Adaptive Directional Loss (RNAD), a model-agnostic training objective that combines online volatility normalization, adaptive interpolation between quadratic and Charbonnier penalties, and gated directional supervision that suppresses learning from near-zero returns. RNAD requires only a lightweight per-asset volatility buffer and integrates seamlessly into existing forecasting models without architectural modifications or inference overhead. Evaluated across nine financial assets, four state-of-the-art forecasting backbones, and strict chronological train-validation-test splits, RNAD consistently achieves the lowest RMSE while improving MAE and directional accuracy. Ablation studies identify directional supervision as the primary source of improvement, with tail-aware and noise-aware gating providing complementary regime-dependent benefits. These findings demonstrate that objective design offers a simple, effective, and broadly applicable path to improving financial time-series forecasting.

30 October 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Nabeel Ahmad SaiddNabeel Ahmad Saidd
Nabeel Ahmad Saidd
Reinforcement learning (RL) for foreign exchange (Forex) trading requires realistic execution modeling, interpretable reward design, and action spaces that respect market constraints. Existing approaches often simplify these aspects, limiting policy transparency and practical relevance. This paper presents a modular RL framework integrating three components: (1) a friction-aware execution engine enforcing anti-lookahead semantics—observations at closet, execution at opent+1, and mark-to-market at closet+1—while modeling spread, commission, slippage, rollover financing, and margin-triggered liq-uidation; (2) a decomposable 11-component reward architecture with fixed, pre-specified weights and per-step logging, enabling attribution, ablation, and auditability; and (3) a 10-action discrete interface supporting scaling, reduction, closure, and reversal, with legal-action masking enforcing margin-aware feasibility during training and evaluation. Empirical evaluation on EURUSD training-split data reveals non-monotonic interactions among reward components, demonstrating that additional penalties do not consistently improve performance. The full reward configuration achieves a terminal training Sharpe ratio of 0.765 and cumulative return of 57.09%. Comparing action spaces, the extended 10-action interface increases cumulative return but reduces Sharpe relative to a conservative 3-action variant, revealing a return–activity trade-off under a fixed training budget. Scaling-enabled strategies consistently reduce drawdowns, with the combined configuration delivering the strongest endpoint performance. Supplementary diagnostics on GBPUSD, USDJPY, and AUDUSD exhibit qualitatively similar trends. These findings demonstrate the framework’s diagnostic value and underscore the importance of controlled, interpretable design in RL-based financial systems.

4 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Nabeel Ahmad SaiddNabeel Ahmad Saidd
Nabeel Ahmad Saidd
The effectiveness of conventional technical indicators in deep learning-based financial forecasting remains an open empirical question. This study presents a large-scale ablation analysis of their contribution to next-day price prediction using recurrent neural networks. We conduct 500 controlled experiments across 10 assets representing five asset classes: commodities, cryptocurrencies, equities, foreign exchange, and market indices, using daily OHLCV data from 2010 to 2025. Five feature configurations are evaluated: raw OHLCV inputs and four indicator-augmented variants incorporating momentum, trend, volatility, and all indicators. Each configuration is assessed using LSTM and GRU architectures across five random seeds. Results demonstrate that technical indicators generally fail to improve forecasting performance and frequently increase prediction errors. The raw OHLCV baseline achieves the lowest mean RMSE (\(0.166 \pm 0.148\)) and highest mean directional accuracy (\(55.7\% \pm 5.5\%\)). The comprehensive indicator configuration increases RMSE by \(34.6\%\) (\(p < 0.001\), Cohen's \(d = -0.29\)), while all four indicator categories exhibit statistically significant performance degradation at \(\alpha = 0.05\). GRU models achieve higher directional accuracy than LSTM models (\(55.3\%\) versus \(51.0\%\)), although their RMSE difference is not statistically significant (\(p = 0.846\)). Foreign exchange is the only asset class benefiting from volatility indicators, with a \(4.2\%\) RMSE reduction, whereas cryptocurrencies and commodities exhibit \(83\%\) higher mean prediction error than lower-volatility assets. These findings suggest that recurrent networks may implicitly learn patterns represented by conventional indicators, rendering explicit indicator features redundant or detrimental. The results underscore the importance of rigorous baseline comparisons and evidence-driven feature selection in neural network-based financial forecasting.

4 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Nabeel Ahmad SaiddNabeel Ahmad Saidd
Nabeel Ahmad Saidd
Financial time-series forecasting is commonly optimized with mean squared error (MSE), yet volatility clustering, heavy tails, and regime shifts make a fixed quadratic objective poorly suited. Existing robust losses improve resistance to extreme errors but lack adaptive volatility normalization and explicit directional supervision, while directional objectives such as Generalized Mean Absolute Directional Loss (GMADL) do not integrate volatility scaling, tail adaptation, and noise-aware directional weighting. We introduce Regime-Normalized Adaptive Directional Loss (RNAD), a model-agnostic training objective combining online volatility normalization via batch-scale estimates and an exponential moving average, tail-gated interpolation between quadratic and Charbonnier penalties, and noise-gated directional supervision that attenuates near-zero returns. RNAD requires no architectural changes, adds only a scalar state buffer, and incurs no inference-time overhead. Across nine financial assets, four architectures (PatchTST, iTransformer, N-HiTS, TimeXer), five losses, and three seeds under chronological splits, RNAD achieves the lowest mean RMSE for every backbone, reducing RMSE by 0.086–0.882 units versus the strongest non-RNAD baseline. It also improves MAE and directional accuracy (DA), with the lowest RMSE on all nine assets when paired with PatchTST. Four-step forecasts on US500 and USDJPY improve average DA by 2.39 and 1.41 percentage points, respectively, and reduce flattened RMSE on US500 by 0.3%. Ablations identify directional supervision as the main contributor, with tail adaptation and noise gating providing complementary, regime-dependent gains. Overall, adaptive, volatility-aware loss design offers a lightweight route to better numerical accuracy and directional consistency across financial forecasting architectures.

22 September 2026 in SSRN Electronic Journal
Verified
Preprint
Open access
Nabeel Ahmad SaiddNabeel Ahmad Saidd
Nabeel Ahmad Saidd
Financial time series evolve across multiple temporal resolutions, challenging forecasting systems to incorporate newly available information without repeatedly recomputing unchanged representations. We introduce HARN, a Hierarchical Associative Resonance Network for event-driven multi-timeframe forecasting. HARN maintains persistent representations across temporal levels and updates each level only when its corresponding completed bar becomes available. The architecture combines causal multi-scale temporal encoding, gated associative memory, cross-level resonance, and hierarchical evidence aggregation, with forecasting performed in basis-point space and reconstructed to the original price scale. We evaluate HARN on four assets spanning equity, foreign exchange, and commodity markets using multiple random seeds and component ablations. HARN achieves competitive reconstructed-price forecasting errors against single-timeframe PatchTST and TimeXer baselines, while ablations reveal the effects of removing individual components across assets and timeframes. A code-level audit further examines consistency between the implementation and the defined event-driven causal protocol. The results position HARN as a persistent multi-timeframe forecasting framework rather than evidence of universal predictive superiority.

3 November 2026 in Preprints.org
Verified
Preprint
Open access
PDF file
Nabeel Ahmad SaiddNabeel Ahmad Saidd
Nabeel Ahmad Saidd
Live financial forecasting must synchronize asynchronous bar completions across timeframes without using stale or unavailable information. We introduce HARN (Hierarchical Associative Resonance Network), an event-driven architecture that anchors each event to the finest configured timeframe and maintains persistent states and matrix-valued associative memories across temporal levels. Its timestamp-masked transition updates a level only when its completed-bar timestamp matches the current anchor, preserving inactive representations. HARN integrates causal multi-scale encoding, residual-driven gated associative writes, all-to-all cross-level resonance, and ordered bottom-up evidence aggregation to produce forecasts at each temporal level. Predictions are expressed as basis-point changes and reconstructed on the price scale for evaluation. We evaluate HARN on four assets spanning equities, foreign exchange, and gold (AAPL, EURUSD, USDCHF, and XAUUSD), using chronological 70/15/15 splits, 32-bar lookbacks, one-step horizons, and three random seeds. HARN obtains lower anchor-timeframe test mean absolute errors (MAEs) than the evaluated single-timeframe PatchTST and TimeXer baselines on all four assets. HARN's MAEs are 0.508, 0.000306, 0.000263, and 2.552, respectively; PatchTST records 2.074, 0.000759, 0.000638, and 9.563, while TimeXer records 2.882, 0.010838, 0.014144, and 15.297. These descriptive comparisons do not isolate architectural effects from differences in inputs, target formulations, or training procedures. Single-run component ablations on AAPL and EURUSD show small, non-monotonic differences. The results demonstrate HARN's feasibility for asynchronous multi-timeframe forecasting, while motivating controlled comparisons and broader ablations to establish its relative advantages and component contributions.