Biman Rimal | Searcharxiv

arXiv2026

Modeling the Dynamic Relationship Between Brent Crude Oil Prices and the Nepal Stock Exchange: An Integrated Econometric and Explainable Machine Learning Approach

This study examines the dynamic relationship between the global oil prices and Nepal Stock Exchange (NEPSE) using an integrated approach which combines traditional econometric techniques with machine learning and explainable AI techniques. For this, Daily data of International Oil prices and NEPSE index is analyzed from approximately thirteen years (June 2013 to June 2026) using Granger causality, EGARCH(1,1), and DCC-GARCH models to examine different properties like predictive relationships, asymmetric volatility behaviour, and time-varying correlations. To further supplement the econometric analysis, Machine Learning Models like Random Forest, LightGBM, and XGBoost algorithms were used to capture nonlinear relationships, along with explainable artificial intelligence techniques like SHAP values, Partial Dependence Plots, and Individual Conditional Expectation plots to further interpret the results of the model. The results from the econometric analysis showed a statistically significant unidirectional Granger causality from Brent crude oil to NEPSE with a four-day lag, high volatility persistence in both markets, and weak yet highly time-varying conditional correlations. Among the machine learning models, XGBoost achieves the best performance, and explainability analysis reveals that NEPSE own momentum and short-term volatility mainly influence its own behaviour and oil-related information serves as a minor, method-dependent contributor. The findings demonstrate that econometric and explainable machine learning approaches provide insights into the oil and equity market relationship in a way that each approach complements the result of one another.

econ.EM↗

arXiv2026

A Closed-Form Dual-Barrier CBF Safety Filter for Holonomic Robots on Incrementally Built Occupancy Grid Maps

We present a dual-barrier control barrier function (CBF) safety filter for real-time, safety-critical velocity control of holonomic robots operating in incrementally built occupancy grid maps. As a robot explores an unknown environment, unmapped regions introduce irreducible uncertainty, since obstacle geometry beyond the explored frontier is unknown, making entry into such regions a source of collision risk, especially with front-facing sensors. To address this, we enforce two constraints: avoidance of mapped obstacles and restriction from unexplored regions. Both constraints are derived analytically from the occupancy grid's signed distance field, yielding a closed-form safety filter that requires only a small linear system solve per cycle. On resource-constrained platforms such as the Raspberry Pi, where SLAM and planning already consume significant compute, the low overhead of the proposed filter preserves resources. An adaptive gain schedule relaxes the frontier constraint in information-rich regions and tightens it in well-mapped areas, improving exploration efficiency while maintaining safety. The filter operates in velocity space as a minimally invasive correction and composes with arbitrary nominal controllers, including learning-based methods. Hardware flight experiments on a PX4-controlled quadrotor demonstrate zero collisions across multiple indoor runs.

cs.RO↗