Niraj Neupane
Financial Markets · Quantitative Finance · AI/ML Engineering · Mathematics & Financial Econometrics
Financial Markets · Quantitative Finance · AI/ML Engineering · Mathematics & Financial Econometrics
I am Niraj Neupane, a Chartered Accountant and financial economics professional with a deep interest in financial markets, quantitative finance, AI/ML engineering, mathematics, and financial econometrics.
My work and interests lie at the intersection of financial theory, mathematical modeling, econometrics, machine learning, and computational methods. I am particularly interested in using data, mathematical models, and intelligent systems to understand financial markets and develop quantitative, data-driven solutions.
Financial Markets
Market dynamics, derivatives, trading, market microstructure, and risk.
AI/ML Engineering
Machine learning, deep learning, financial time series, and intelligent financial systems.
Mathematics
Probability, statistics, optimization, stochastic processes, and mathematical modeling.
Financial Econometrics
Time-series analysis, volatility modeling, forecasting, empirical finance, and statistical inference.
Description:
ML-LiqVaR is a quantitative risk framework that combines machine learning, liquidity risk, and Value at Risk (VaR) to study market risk under changing market and liquidity conditions. The project explores how machine-learning techniques can complement traditional quantitative risk methodologies and provide more flexible risk estimates when liquidity conditions change.
The framework sits at the intersection of financial econometrics, market-risk modeling, machine learning, and quantitative finance, with a focus on understanding how liquidity can influence the measurement and forecasting of financial risk.
Key areas:
Machine Learning · Liquidity Risk · VaR · Market Risk · Financial Econometrics · Quantitative Finance
Technology: Python · Jupyter Notebook
Website button: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7222958
Description:
This project applies machine learning to quantitative financial risk estimation and forecasting. The work covers VaR forecasting, volatility prediction, credit-risk analysis, anomaly detection, and model explainability using SHAP-based methods.
The project focuses on how machine-learning models can be incorporated into financial-risk workflows to identify patterns in market data, improve risk forecasting, and provide greater insight into model predictions. It connects traditional risk-management concepts with modern AI/ML techniques.
Key areas:
Machine Learning · Risk Forecasting · VaR · Volatility · Credit Risk · Anomaly Detection · Explainable AI
Technology: Python · Machine Learning · SHAP
Website button: https://github.com/nirajneupane17/ML-Risk-Estimation-Forecasting
Description:
This project investigates financial-market volatility using econometric volatility models, including GARCH, EGARCH, and HAR-RV approaches. The work includes rolling estimation, regime analysis, volatility forecasting, and evaluation of forecast performance.
The project demonstrates how econometric models can be used to understand the time-varying nature of financial-market volatility and develop quantitative forecasts from financial time-series data.
It represents the Financial Econometrics + Mathematics side of your profile and complements your machine-learning risk projects by providing a traditional econometric framework for volatility analysis.
Key areas:
Financial Econometrics · Volatility Modeling · Time Series · GARCH · EGARCH · HAR-RV · Forecasting
Technology: Python · Jupyter Notebook
Website button: https://github.com/nirajneupane17/GARCH-Volatility-Forecasting/tree/main
Description:
This project applies Monte Carlo simulation and quantitative methods to portfolio risk estimation and derivatives pricing. It explores Geometric Brownian Motion, variance-reduction techniques, path-dependent derivatives, and convergence analysis.
The project demonstrates the use of computational simulation to model uncertain financial outcomes and estimate both portfolio risk and derivative values. It connects mathematical modeling, probability, numerical methods, and financial derivatives.
This is one of the projects that best represents your interest in mathematical finance.
Key areas:
Monte Carlo Simulation · Derivatives Pricing · Portfolio Risk · Geometric Brownian Motion · Variance Reduction · Numerical Methods
Technology: Python · Jupyter Notebook
Website button: https://github.com/nirajneupane17/Monte-Carlo-Risk-Derivatives-Pricing
Description:
This project explores the mechanics of financial-market microstructure and trading execution through order-book analysis. It examines bid-ask spread decomposition, Kyle's lambda, Amihud illiquidity, market impact, VWAP/TWAP execution, and optimal trade scheduling.
The project focuses on how orders interact with market liquidity and how trading decisions can affect execution costs and market impact. It provides a practical connection between market microstructure, liquidity, quantitative trading, and execution analytics.
This project is especially valuable because it shows that your interest in financial markets extends beyond risk models into how markets actually function and how trades are executed.
Key areas:
Market Microstructure · Order Books · Liquidity · Market Impact · Execution · VWAP · TWAP · Trade Scheduling
Technology: Python
Website button: https://github.com/nirajneupane17/Order-Book-Microstructure-Market-Impact/tree/main
Description:
This project develops a quantitative framework for statistical arbitrage and pairs trading, using statistical relationships between securities to identify potential trading opportunities.
The work includes cointegration testing, Engle-Granger and Johansen methodologies, Z-score signals, Kalman filtering, Kelly-based position sizing, and transaction-cost-aware backtesting.
The project combines financial econometrics, statistical modeling, portfolio construction, and quantitative trading. It demonstrates how statistical relationships in financial time series can be translated into systematic trading strategies and evaluated through historical backtesting.
Key areas:
Statistical Arbitrage · Pairs Trading · Cointegration · Engle-Granger · Johansen · Kalman Filter · Backtesting · Position Sizing
Technology: Python
Website button: https://github.com/nirajneupane17/Statistical-Arbitrage-Pairs-Trading
University of Wisconsin–Madison
Description
Graduate training in financial economics with an emphasis on quantitative analysis, financial markets, investment theory, derivatives, corporate finance, econometrics, and data-driven financial analysis. The program strengthened my ability to combine economic theory, statistical methods, and computational tools to analyze financial markets and risk.
Selected Coursework
Financial Mathematics
Investment Theory
Analysis of Fixed Income Securities
Derivatives & Advanced Securities Analysis
Corporate Finance
Financial Econometrics
Machine Learning for Economists
Economic Statistics & Econometrics
Quantitative Financial Analysis
Academic Focus
Quantitative Finance · Financial Econometrics · Financial Markets · Risk Management · Machine Learning
WorldQuant University
Description
Advanced quantitative training focused on financial engineering, mathematical modeling, computational finance, quantitative risk analysis, and applications of programming and statistical methods to financial problems.
Selected Coursework / Areas of Study
Financial Engineering
Quantitative Modeling
Computational Finance
Derivatives
Risk Modeling
Statistical & Mathematical Methods
Financial Data Analysis
Academic Focus
Mathematical Finance · Quantitative Modeling · Computational Finance · Derivatives · Risk
University of London
Description
Interdisciplinary academic foundation combining mathematics and economics, providing the theoretical basis for quantitative modeling, statistics, econometrics, optimization, economic analysis, and financial applications.
Academic Focus
Mathematics · Statistics · Economics · Econometrics · Quantitative Analysis · Mathematical Modeling
The Institute of Chartered Accountants of India (ICAI)
Description
Professional qualification in accounting and finance with a strong foundation in financial reporting, auditing, taxation, corporate finance, financial analysis, internal controls, risk management, and regulatory compliance.
The CA qualification provides an important foundation for my transition into quantitative finance and financial risk, combining traditional financial expertise with quantitative and computational methods.
Core Professional Areas
Financial Accounting & Reporting
Auditing & Assurance
Financial Management
Taxation
Risk Management
Internal Controls
Corporate Governance
Regulatory Compliance
Financial Analysis
Capital Markets & Financial Analysis
My professional development has increasingly focused on quantitative finance, market risk, derivatives, financial econometrics, machine learning, and financial engineering.
Areas of Professional Interest
Financial Markets · Quantitative Finance · Market Risk · Model Risk · Financial Econometrics · Machine Learning · Derivatives · Systematic Trading
A professional risk-management pathway focused on understanding and measuring financial risks across financial institutions and markets.
Key areas of study:
Market Risk
Credit Risk
Operational Risk
Quantitative Analysis
Risk Measurement & Management
Financial Markets & Products
Valuation and Risk Models
Risk Management Frameworks
Relevance to my profile:
Strengthens my foundation in quantitative risk management and supports my interests in market risk, model risk, financial markets, and quantitative finance.
Advanced finance and quantitative modeling training focused on applying analytical and mathematical approaches to financial decision-making.
Key areas of study:
Financial Modeling
Quantitative Analysis
Financial Markets
Valuation
Investment Analysis
Risk Analysis
Financial Decision-Making
Relevance to my profile:
Connects financial theory with quantitative modeling and supports my broader focus on quantitative finance and financial-market analysis.
Professional certification focused on the structure and functioning of global capital markets and the analysis of securities and financial instruments.
Key areas of study:
Capital Markets
Equities
Fixed Income
Derivatives
Foreign Exchange
Securities Analysis
Financial Markets & Instruments
Investment Analysis
Market Participants
Relevance to my profile:
Provides a practical capital-markets foundation that complements my quantitative finance, derivatives, market-risk, and financial-econometrics interests.
Market-focused training designed to develop practical understanding of global financial markets and the use of market data.
Key areas of study:
Economic Indicators
Equities
Fixed Income
Foreign Exchange
Commodities
Financial Market Data
Market Analysis
Bloomberg Terminal & Market Information
Relevance to my profile:
Strengthens my understanding of financial-market data and market instruments and complements my quantitative research and financial-market analysis.
Specialized training focused on fixed-income investments, portfolio construction, and the measurement and management of interest-rate and portfolio risks.
Key areas of study:
Fixed Income Markets
Bond Portfolio Construction
Interest-Rate Risk
Duration
Convexity
Portfolio Risk
Yield Curves
Fixed Income Investment Analysis
Relevance to my profile:
Directly supports my interests in fixed-income markets, quantitative risk, portfolio construction, and mathematical finance.
Technical training focused on using Python and data-science methodologies for analytical and machine-learning applications.
Key areas of study:
Python Programming
Data Analysis
NumPy & Pandas
Data Visualization
Machine Learning
AI Concepts
Data Preparation
Model Development
Relevance to my profile:
Supports my transition toward AI/ML Engineering and provides the computational foundation for applying machine learning to financial markets, risk, and econometric problems.
Specialized training focused on financial risk management, internal controls, governance, and risk-control frameworks within financial institutions.
Key areas of study:
Financial Risk
Risk Controls
Internal Controls
Risk Governance
Control Frameworks
Financial Institutions
Risk Identification & Mitigation
Regulatory Environment
Relevance to my profile:
Connects my professional accounting background with financial risk, controls, governance, and institutional risk management.
Academic study of the global financial crisis and the mechanisms through which financial-market and institutional risks can develop into systemic crises.
Key areas of study:
Financial Crisis
Systemic Risk
Financial Institutions
Credit Markets
Housing & Mortgage Markets
Financial Regulation
Crisis Transmission
Policy Responses
Relevance to my profile:
Deepens my understanding of financial-market structure, systemic risk, and the relationship between financial institutions and broader market stability.
Professional financial-modeling training focused on building analytical models and evaluating companies, investments, and financial decisions.
Key areas of study:
Financial Modeling
Financial Statements
Forecasting
Valuation
Corporate Finance
Investment Analysis
Financial Analysis
Scenario & Sensitivity Analysis
Relevance to my profile:
Provides a practical foundation in financial modeling and valuation that complements my quantitative finance and financial-analysis background.
Specialized markets training focused on the structure and activities of institutional sales and trading businesses.
Key areas of study:
Financial Markets
Sales & Trading
Market Instruments
Trading Activities
Market Participants
Risk Management
Market-Making
Institutional Markets
Relevance to my profile:
Particularly relevant to my interest in financial markets, trading, derivatives, market risk, and quantitative finance.
Foundation-level training covering the investment industry, financial markets, investment products, ethics, and the investment-management process.
Key areas of study:
Investment Industry
Financial Markets
Equity Investments
Fixed Income
Derivatives
Alternative Investments
Portfolio Management
Investment Ethics
Professional Standards
Relevance to my profile:
Provides broad investment-industry knowledge and complements my academic and professional specialization in financial markets and quantitative finance.
Nathan S. Brand Award: Excellence in Investment Banking & Finance Presentation
Recognition for excellence in finance and investment-banking presentation.
McKinsey Global Leadership & Exchange Program
Participation in a global leadership and professional-development program.
International Model United Nations Conference
21st World Congress of Accountants
International Conference on Accountancy Profession: Augmenting Economic Sustainability
I write about the intersection of financial markets, quantitative finance, financial econometrics, AI/ML engineering, and risk management. My articles explore both traditional quantitative methods and emerging computational approaches, with an emphasis on connecting financial theory, mathematical modeling, and machine learning with practical applications in markets, trading, and risk.
Through these insights, I aim to examine not only how quantitative models work, but also their assumptions, limitations, validation requirements, and behavior under changing market conditions.
Understanding Risk Horizons in Market Risk
Value at Risk depends not only on the confidence level and methodology used, but also on the time horizon over which potential losses are measured. This article explores the differences between 1-day and 10-day VaR, the square-root-of-time scaling approach, its underlying assumptions, and why volatility clustering, liquidity conditions, nonlinear exposures, and market stress can challenge simple VaR scaling.
Topics: Value at Risk · Market Risk · Risk Horizons · Expected Shortfall · Risk Modeling
Read Article: 1-Day VaR vs. 10-Day VaR
From Traditional Risk Models to AI-Driven Risk Analytics
Machine learning is creating new possibilities for financial-risk measurement and forecasting. This article examines how ML can complement traditional approaches such as Historical VaR, Monte Carlo VaR, Expected Shortfall, GARCH, stress testing, and scenario analysis through applications including volatility forecasting, risk prediction, anomaly detection, and market-regime identification.
It also explores important challenges surrounding overfitting, explainability, model drift, backtesting, validation, and model governance.
Topics: Machine Learning · Market Risk · VaR · Risk Forecasting · Model Validation · Explainable AI
Read Article: Machine Learning in Market Risk
Comparing Econometric and AI-Based Approaches
Volatility forecasting plays an important role in portfolio risk, derivatives pricing, hedging, asset allocation, and quantitative trading. This article compares traditional financial-econometric approaches such as GARCH, EGARCH, and HAR-RV with machine-learning methods capable of capturing more complex and nonlinear relationships in financial data.
Rather than asking which methodology is universally superior, the article considers their differences in interpretability, flexibility, model complexity, out-of-sample performance, and behavior across changing market regimes.
Topics: GARCH · EGARCH · Volatility · Machine Learning · Time Series · Financial Econometrics
Read Article: GARCH vs. Machine Learning for Volatility Forecasting
Why Market Liquidity Matters for Financial Risk Measurement
Traditional market-risk measures can underestimate an important source of potential loss: the cost of liquidity. This article examines how bid-ask spreads, market depth, transaction costs, trading volume, and price impact can affect portfolio losses, particularly during periods of financial-market stress.
It also explores the relationship between liquidity-adjusted risk measurement and machine learning, providing a natural connection to my ML-LiqVaR research.
Topics: Liquidity Risk · VaR · Market Risk · Market Microstructure · Machine Learning · ML-LiqVaR
Read Article: Liquidity Risk and VaR
Building Data-Driven Trading Strategies
Machine learning provides powerful tools for extracting information from financial data, but building a successful quantitative trading system requires much more than selecting an algorithm. This article explores the complete process from market data and feature engineering to signal generation, portfolio construction, backtesting, execution, and risk management.
It also discusses statistical arbitrage, momentum and mean-reversion strategies, factor models, regime detection, and critical risks such as overfitting, look-ahead bias, data leakage, transaction costs, and changing market regimes.
Topics: AI/ML · Quantitative Trading · Statistical Arbitrage · Factor Models · Backtesting · Systematic Trading
Read Article: AI/ML in Quantitative Trading
Understanding Orders, Liquidity, Execution and Market Impact
Understanding financial markets requires looking beyond price movements to examine how trading actually occurs. This article explores order books, bid-ask spreads, market depth, liquidity, Kyle's lambda, Amihud illiquidity, market impact, and institutional execution.
It also examines VWAP, TWAP, and optimal trade scheduling, highlighting how transaction costs, execution speed, liquidity, and market impact can influence the real-world performance of quantitative trading strategies.
Topics: Market Microstructure · Order Books · Liquidity · Market Impact · VWAP · TWAP · Algorithmic Trading
Read Article: Market Microstructure and Algorithmic Trading
My Writing & Insights section continues to explore ideas across financial markets, quantitative finance, financial econometrics, machine learning, mathematical finance, derivatives, risk management, and systematic trading.
I am always interested in connecting with professionals, researchers, and organizations working at the intersection of financial markets, quantitative finance, AI/ML engineering, financial econometrics, mathematical finance, and risk management.
Whether you are interested in quantitative research, financial engineering, market risk, systematic trading, machine learning, or research collaboration, I would be happy to connect, exchange ideas, and explore opportunities to work together.
LinkedIn: https://www.linkedin.com/in/nirajneupane17/
Connect with me professionally and follow my work, research interests, and career journey.
GitHub: https://github.com/nirajneupane17
Explore my quantitative finance, financial econometrics, machine learning, risk-management, and trading projects.
Research: https://papers.ssrn.com/sol3/papers.cfm?abstract_id=7170418
Explore my research interests, quantitative work, publications, and ML-driven financial research.
Email: nirajneupane17@gmail.com
For professional opportunities, research collaboration, or discussions related to quantitative finance and financial markets.
Exploring markets. Building models. Applying mathematics and AI to financial problems.