Contributing Author · Quantitative Research
Niraj Neupane
CHARTERED ACCOUNTANT (ICAI)• QUANTITATIVE FINANCE RESEARCHER• AI/ML IN FINANCIAL MARKETS
Quantitative Finance• Financial Econometrics• AI/ML• Trading• Risk Management• Model Validation• Financial Technology
About
Niraj Neupane is a Chartered Accountant (ICAI) and quantitative finance researcher working at the intersection of financial economics, financial econometrics, artificial intelligence, machine learning, quantitative modeling, and financial markets.
His research examines how quantitative and AI/ML methods can be developed, tested, validated, and responsibly applied across financial-market activities, including quantitative research, systematic trading, market and liquidity risk management, financial forecasting, regulatory and compliance applications, and financial-model governance.
His work spans financial risk measurement, Value-at-Risk, Expected Shortfall, liquidity-adjusted risk, volatility modeling, quantitative trading, financial econometrics, machine-learning forecasting, model validation, stress testing, regime-aware analysis, and responsible AI.
A central theme of his research is the reliability of quantitative and machine-learning models: whether models that perform well under historical or normal conditions continue to provide useful, robust, interpretable, and defensible results when markets experience volatility, liquidity changes, structural shifts, and stress.
Through his research and technical projects, Niraj aims to contribute to the responsible and effective application of artificial intelligence, machine learning, and automation across trading, risk management, regulatory compliance, and quantitative research in financial markets.
Background
Niraj Neupane is a Chartered Accountant (ICAI) and quantitative finance researcher with academic training in economics, finance, financial economics, and quantitative methods. His work combines financial econometrics, statistical modeling, machine learning, financial engineering, programming, and practical financial-market analysis.
His research interests extend across quantitative finance and financial technology, including financial forecasting, market and liquidity risk, Value-at-Risk, Expected Shortfall, volatility modeling, derivatives, quantitative trading, portfolio analytics, financial econometrics, machine learning, model validation, stress testing, and financial-market applications of artificial intelligence.
A central area of his work is the development and validation of quantitative models. This includes examining how models perform across different market regimes, how model selection can introduce overfitting, how forecasts can become miscalibrated, and how validation frameworks can identify weaknesses that may not be visible through conventional performance measures.
His broader research agenda examines how artificial intelligence, machine learning, and automation can be responsibly integrated into financial-market activities while maintaining appropriate standards of reliability, transparency, validation, governance, and human oversight.
Research & Working Papers
Research papers, working papers, and research in progress covering quantitative finance, financial econometrics, artificial intelligence, machine learning, financial risk management, quantitative trading, and model validation.
SSRN Working Paper · Abstract 7222958
ML-LiqVaR: A Liquidity- and Regime-Aware, Extreme-Value-Calibrated Gradient-Boosting Value-at-Risk Model for US Equities
A quantitative framework for one-day-ahead Value-at-Risk forecasting that combines volatility modeling, Extreme Value Theory, gradient-boosted quantile regression, liquidity and volatility features, and regime-aware modeling.
The research examines whether machine-learning methods can improve tail-risk measurement while maintaining rigorous statistical validation and providing a more comprehensive representation of market conditions.
SSRN Working Paper · Abstract 7170418 · July 2026
Backtesting Value-at-Risk Models Under SR 11-7: A Comparative Analysis of Kupiec, Christoffersen, and Basel Traffic-Light Tests Applied to S&P 500 Returns
A walk-forward empirical study of Value-at-Risk models using S&P 500 daily returns. The research compares unconditional coverage, conditional coverage, and Basel traffic-light backtesting approaches and examines their relevance to quantitative model validation and financial risk management.
Working Paper
When Backtests Lie: A Governance-Grade Validation Framework for Machine-Learning Value-at-Risk Models under Regime Shifts
This research develops a governance-oriented validation framework for machine-learning Value-at-Risk models.
The framework extends conventional backtesting with regime-conditional coverage analysis, Probability of Backtest Overfitting, and conformal recalibration to examine whether aggregate model evaluation can conceal weaknesses during stressed or changing market conditions.
The research connects statistical forecast evaluation with practical model-risk governance and develops a reproducible framework for assessing the reliability, robustness, and calibration of machine-learning risk models.
Research Trajectory
Risk Measurement→ Quantitative Modeling→ Backtesting→ Machine Learning→ Model Validation→ Responsible AI
01
ML-LiqVaR
Developing machine-learning methods for liquidity-aware, regime-aware, and tail-risk-sensitive Value-at-Risk estimation.
02
VaR Backtesting Under SR 11-7
Examining conventional statistical backtesting and quantitative model-validation approaches for financial risk models.
03
Governance-Grade ML Validation
Extending conventional validation to regime robustness, model-selection risk, calibration, and governance of machine-learning risk models.
Research Focus
My research focuses on the responsible and effective application of artificial intelligence, machine learning, quantitative methods, and automation to financial markets.
- Quantitative Finance and Financial Engineering
- Artificial Intelligence and Machine Learning in Financial Markets
- Financial Econometrics and Time-Series Modeling
- Quantitative Trading and Systematic Research
- Market and Liquidity Risk Management
- Value-at-Risk and Expected Shortfall
- Financial Forecasting and Volatility Modeling
- Model Validation and Model Risk Management
- Stress Testing and Regime-Aware Analysis
- Regulatory and Compliance Applications
- Explainable AI and Financial Model Governance
- Responsible AI for Financial Institutions
Areas of Research
AI & Machine Learning in Financial Markets
Machine-learning methods for financial forecasting, quantitative research, risk measurement, anomaly detection, model development, and financial-market applications.
Quantitative Finance
Quantitative modeling, financial engineering, derivatives, portfolio analytics, systematic strategies, financial forecasting, and computational finance.
Financial Econometrics
Financial time-series analysis, volatility modeling, GARCH-family models, quantile regression, forecasting, regime identification, and statistical inference.
Market & Liquidity Risk
Value-at-Risk, Expected Shortfall, liquidity-adjusted risk, tail-risk measurement, stress testing, volatility, and regime-dependent financial risk.
Quantitative Trading & Research
Systematic research, feature engineering, signal development, portfolio analysis, backtesting, quantitative strategies, and model evaluation.
Model Validation
Backtesting, coverage testing, benchmarking, calibration, stability analysis, robustness testing, model-selection risk, and validation frameworks.
Regulatory & Compliance Analytics
AI/ML applications for financial surveillance, anomaly detection, regulatory analytics, compliance monitoring, and quantitative assessment of financial-market activity.
Responsible AI & Financial Governance
Explainability, model risk management, monitoring, documentation, governance, validation, auditability, and responsible deployment of AI/ML systems in financial institutions.
Research Questions
- How can artificial intelligence and machine learning improve quantitative financial modeling while maintaining appropriate standards of reliability and validation?
- How can machine-learning models be validated when financial markets experience structural changes, volatility shifts, liquidity deterioration, or stressed conditions?
- Can conventional backtesting adequately identify the weaknesses of flexible machine-learning risk models?
- How can liquidity, volatility, and market-regime information be incorporated into financial risk models?
- How can AI and quantitative methods support systematic trading and quantitative research?
- How can machine-learning models be monitored for instability, overfitting, calibration deterioration, and model drift?
- How can explainability, validation, and governance improve the responsible use of AI in financial institutions?
- How can AI and automation support financial-market compliance and regulatory applications while maintaining appropriate human oversight?
Research Philosophy
A financial model should not be judged only by how well it performs under normal conditions. It should also be evaluated for stability, calibration, robustness, interpretability, and failure behavior when markets change.
My research therefore considers the broader lifecycle of quantitative and machine-learning models—from problem formulation and development to empirical testing, validation, monitoring, governance, and practical deployment.
The objective is not simply to build models that perform well, but to understand when they work, when they fail, why they fail, and how those failure modes can be identified and managed.
Technical & Quantitative Methods
Financial Econometrics
- Time-series analysis
- Volatility modeling
- GARCH-family models
- Quantile regression
- Forecasting
- Regime analysis
- Statistical testing
Machine Learning
- Supervised learning
- Gradient boosting
- Quantile machine learning
- Feature engineering
- Model evaluation
- Anomaly detection
- Model monitoring
Financial Engineering
- Value-at-Risk
- Expected Shortfall
- Derivatives
- Portfolio analytics
- Stress testing
- Tail-risk measurement
- Liquidity risk
Quantitative Research
- Systematic research
- Backtesting
- Signal development
- Portfolio construction
- Performance evaluation
- Financial data analysis
Model Validation
- Backtesting
- Benchmarking
- Calibration
- Stability testing
- Robustness analysis
- Overfitting assessment
- Model governance
Computational Finance
- Python
- C++
- R
- SQL
- Pandas
- NumPy
- Scikit-learn
- TensorFlow
- MATLAB
- Statistical and numerical computing
Research & Technology Projects
Alongside academic and independent research, Niraj develops research-oriented technology initiatives designed to translate quantitative finance and AI/ML methodologies into practical financial-market applications.
Korvane
Korvane is a research and technology initiative focused on AI-driven trade, risk, and model-validation applications.
Its conceptual scope includes quantitative research, market-risk analytics, liquidity and stress analysis, model validation, monitoring, explainability, and financial decision-support workflows.
The initiative is intended to connect quantitative research methodologies with practical financial-market technology.
Calderyn Institute
Calderyn Institute is a research and education initiative focused on developing quantitative and AI/ML capabilities for financial-market applications.
Its proposed areas include quantitative trading, quantitative research, quantitative development, financial risk, model validation, financial engineering, and responsible AI for finance.
Future Research Directions
The continuing research program will explore the development, validation, and responsible deployment of AI and quantitative methods across financial markets.
Key directions include:
- Machine-learning risk measurement
- Liquidity-adjusted and regime-aware risk models
- AI-based stress testing
- Explainable AI for financial models
- Machine-learning model validation
- Quantitative trading and systematic research
- AI-assisted financial-market surveillance
- Regulatory and compliance analytics
- Model monitoring and model-drift detection
- Responsible AI and financial-model governance
- AI/ML applications in quantitative finance and financial engineering
About This Research
Niraj Neupane contributes independent research on quantitative finance, financial economics, financial econometrics, artificial intelligence, machine learning, financial risk management, quantitative trading, and financial-market technology.
Research presented on this site may include working papers, preprints, research in progress, and technical research projects. Unless explicitly identified as peer-reviewed or formally published, a paper should be considered a working paper and should not be interpreted as having undergone formal journal peer review.
Research findings are developed and updated as methodologies, datasets, empirical results, and validation procedures evolve.
The research represents the author's independent views unless a specific institutional or collaborative affiliation is explicitly identified.
Our sourcing, disclosure and corrections policy is set out in the Editorial Standards.