XGBoost Forecasting of NEPSE Index Log Returns with Walk Forward Validation

TL;DR

This paper presents a machine learning framework using XGBoost for accurate one-step-ahead forecasting of NEPSE Index log-returns, employing walk-forward validation to ensure realistic performance assessment in volatile emerging markets.

Contribution

It introduces a comprehensive feature set, hyperparameter optimization, and rigorous validation schemes, establishing a benchmark for NEPSE Index forecasting with gradient boosting models.

Findings

XGBoost outperforms ARIMA and Ridge benchmarks in RMSE and MAE

Expanding window with 20 lags yields best predictive accuracy

Directional accuracy reaches 65.15% in out-of-sample tests

Abstract

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 indicators such as short- and medium-term rolling volatility measures and the 14-period Relative Strength Index. Hyperparameter optimization is performed using Optuna with time-series cross-validation on the initial training segment. 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. Predictive accuracy is evaluated using root mean squared error, mean absolute error, coefficient of determination (R-squared), and directional accuracy on both log-returns and reconstructed closing prices. Empirical results show that 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%. While the R-squared remains modest, consistent with the noisy nature of financial returns, primary emphasis is placed on relative error reduction and directional prediction. Feature importance analysis and visual inspection further enhance interpretability. These findings demonstrate the effectiveness of gradient boosting ensembles in modeling nonlinear dynamics in volatile emerging market time series and establish a reproducible benchmark for NEPSE Index forecasting.