{"paper_id":"2601.08896","title":"XGBoost Forecasting of NEPSE Index Log Returns with Walk Forward Validation","authors":["Sahaj Raj Malla","Shreeyash Kayastha","Rumi Suwal","Harish Chandra Bhandari","Rajendra Adhikari"],"paper_date":"2026-01-13","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2601.08896v1","page_url":"https://thequant.space/flowcharts/xgboost-forecasting-of-nepse-index-log-returns-with-walk-for/","scores":{"empirical_rigor":8.5,"math_complexity":4,"quadrant":"Street Traders"},"proposes":{"status":"available","statement":"The paper proposes a robust XGBoost-based machine learning framework for one-step-ahead forecasting of daily NEPSE Index log‑returns.","quote":"This study develops a robust machine learning framework for one-step-ahead forecasting of daily log-returns in the Nepal Stock Exchange (NEPSE) Index using the XGBoost regressor.","summary":"This study develops a robust machine learning framework for one-step-ahead forecasting of daily log-returns in the Nepal Stock Exchange (NEPSE) Index using the XGBoost regressor. A comprehensive feature set is engineered, including lagged log-returns (up to 30 days) and established technical…","strategy":"XGBoost framework for one-step-ahead forecasting of NEPSE Index log-returns"},"assumptions":{"status":"available","items":[{"assumption":"Log‑returns are stationary and time‑additive, justifying their use as the target variable.","type":"statistical","stated":"implied","quote":"Log-returns are employed due to their desirable statistical properties, including approximate normality and time-additivity, which facilitate modeling in financial time"},{"assumption":"The model relies exclusively on price‑derived features and does not incorporate exogenous macro or news variables.","type":"data","stated":"implied","quote":"The framework relies solely on price-derived features and does not incorporate exogenous variables, such as macroeconomic indicators or news sentiment, which could further improve explanatory power."},{"assumption":"Walk‑forward validation with expanding or fixed‑length windows prevents look‑ahead bias and mimics real‑world deployment.","type":"model","stated":"explicit","quote":"Out-of-sample performance is rigorously assessed via walk-forward validation under both expanding and fixed-length rolling window schemes across multiple lag configurations, simulating real-world deployment and avoiding lookahead bias."},{"assumption":"Hyperparameter tuning is performed only on the initial training segment to avoid data leakage.","type":"data","stated":"explicit","quote":"Hyperparameter optimization is performed using Optuna with time-series cross-validation on the initial training segment."},{"assumption":"The final dataset is split chronologically, reserving the last 20% for out‑of‑sample testing to ensure realistic forecasting conditions.","type":"data","stated":"explicit","quote":"The final dataset is split chronologically, reserving the last 20% of observations exclusively for out-of-sample testing to avoid data leakage and ensure realistic forecasting conditions."}]},"datasets":{"status":"available","items":[{"name":"NEPSE Index daily historical records","provider":"NepseAlpha","kind":"market-prices","access":"public","period":"July 1997–November 2025","universe":"NEPSE Index","quote":"The dataset comprises daily historical records of the NEPSE Index, sourced from the third-party portal NepseAlpha"}],"known":[],"sample":{"start":null,"end":null,"market":"NEPSE Index","asset_class":"equities","frequency":"daily"},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"forecast-accuracy","findings":[{"finding":"The optimal expanding‑window XGBoost configuration (20 lags) achieves the lowest log‑return RMSE of 0.013450, MAE of 0.009814, and directional accuracy of 65.15%, outperforming tuned ARIMA and Ridge benchmarks.","kind":"performance","quote":"The optimal configuration—an expanding window with 20 lags—outperforms tuned ARIMA and Ridge regression benchmarks, achieving the lowest log-return RMSE (0.013450) and MAE (0.009814) alongside a directional accuracy of 65.15%."},{"finding":"Diebold‑Mariano tests indicate the XGBoost model’s predictive superiority over Ridge and ARIMA (p‑values < 0.01).","kind":"statistical","quote":"The DM statistics indicate significant superiority of the optimal XGBoost model (p-values < 0.01 in both pairwise comparisons)."},{"finding":"Feature importance analysis provides interpretable insights into momentum, mean reversion, and volatility clustering.","kind":"other","quote":"Feature importance analysis and visual inspection further enhance interpretability."}],"reported_performance":{"strategy":"XGBoost framework for one-step-ahead forecasting of NEPSE Index log-returns","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"walk-forward","headline_out_of_sample":true}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":28,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":true,"code_url":"https://github.com/sahajrajmalla/nepse-xgboost-forecasting","note":null},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:16:15Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}