Live Monte Carlo Simulation

Real-time Geometric Brownian Motion paths

Move to influence drift Click to spawn paths

Akash Deep

PhD Student in Mathematical Finance

Texas Tech University | Supervised by Dr. Svetlozar Rachev
Specializing in machine learning applications in quantitative finance
Presidential Scholar | 10 Publications | H-Index: 4

10 Publications
32 Citations
3 Kaggle Medals
View Research Get In Touch

About Me

Bridging the gap between mathematics, technology, and finance

I'm a PhD student in Mathematical Finance at Texas Tech University, specializing in quantitative research, trading algorithms, and risk assessment. My work focuses on applying machine learning, stochastic processes, and statistical models to optimize trading strategies and develop AI-powered financial analyst systems.

Academic Excellence

PhD in Mathematical Finance with focus on stochastic processes and quantitative modeling

Research Impact

Published in leading journals with focus on machine learning in financial markets

Innovation

Co-founder of DeepAI Finance LLC, developing AI-powered financial analyst systems

Education Timeline

2024 - 2028

PhD in Mathematical Finance

Texas Tech University

2022 - 2023

MS in Interdisciplinary Studies

Mathematical Finance and Quantum Physics Portfolio

2018 - 2022

BS in Applied Physics

Mathematics Minor, Texas Tech University

Research & Publications

Working under Dr. Svetlozar Rachev (21,000+ citations) on machine learning applications in mathematical finance

Submitted 2025

Probability Weighting Meets Heavy Tails: An Econometric Framework for Behavioral Asset Pricing

arXiv Preprint

Novel econometric framework integrating probability weighting functions from behavioral economics with heavy-tailed distributions for asset pricing, bridging behavioral finance with quantitative risk management.

Co-authors: Svetlozar T. Rachev, Frank J. Fabozzi
Submitted 2025

Binary Tree Option Pricing Under Market Microstructure Effects

Journal of Computational Finance

Developed Random Forest-enhanced binomial tree framework incorporating market microstructure frictions with improved option pricing accuracy while preserving no-arbitrage conditions.

Co-authors: Chris Monico, W. Brent Lindquist, Svetlozar T. Rachev, Frank J. Fabozzi
Published March 2025

Risk-Adjusted Performance of Random Forest Models in High-Frequency Trading

Journal of Risk and Financial Management

Evaluated integration of technical indicators with Random Forest regression models using minute-level SPY data, demonstrating superior risk-adjusted metrics with Rachev ratios between 0.919 and 0.961.

View Publication
Published May 2024

Advanced Financial Market Forecasting: Integrating Monte Carlo Simulations with Ensemble ML Models

Quantitative Finance and Economics

Developed a hybrid model combining Monte Carlo simulations with ML models (Random Forest, LSTM, SVM), improving SPY ETF and major stock predictions by 18% through dynamic risk-adjusted analysis.

View Publication
Under Review 2024

Assessing the Impact of Technical Indicators on Machine Learning Models for Stock Price Prediction

arXiv Preprint

Comprehensive analysis evaluating how technical indicators enhance machine learning model performance in stock price prediction, providing empirical evidence for feature engineering strategies in financial forecasting.

Co-authors: Chris Monico, Abootaleb Shirvani, Svetlozar T. Rachev, Frank J. Fabozzi
Published 2023

Reinforcement Learning in Financial Markets: A Study on Dynamic Model Weight Assignment

International Journal of Computer Science and Telecommunications

Explored reinforcement learning techniques for dynamic portfolio optimization, developing adaptive algorithms that adjust model weights based on market conditions to improve trading performance.

Published 2023

A Multifactor Analysis Model for Stock Market Prediction

International Journal of Computer Science and Telecommunications

Developed a comprehensive multifactor model integrating fundamental, technical, and sentiment analysis factors to enhance stock market prediction accuracy through systematic factor evaluation.

Submitted 2025

Google Trends–Augmented XGBoost for Market Volatility Prediction: A Machine Learning Early-Warning System

Available at SSRN

Novel approach combining Google Trends sentiment data with XGBoost algorithms to create an early-warning system for market volatility, demonstrating improved predictive power through alternative data integration.

Co-authors: Gagan Deep, Svetlozar T. Rachev, Frank J. Fabozzi

Professional Experience

Research, innovation, and leadership in quantitative finance

2024 - Present

PhD Student & Researcher

Mathematical Finance, Texas Tech University

Supervisor: Dr. Svetlozar Rachev

  • Developing statistical models for asset pricing and market microstructure analysis
  • Collaborating with established researchers (Rachev, Fabozzi) on option pricing models
  • Applying machine learning and stochastic processes to high-frequency trading optimization
  • Published research on Random Forest models, Monte Carlo simulations, and reinforcement learning in finance
2022 - Present

Co-Founder & Lead Researcher

DeepAI Finance LLC

  • Developing AI-powered financial analyst platform using advanced ML models and fine-tuned LLMs
  • Applied quantitative research to personal portfolio management and systematic investment strategies
  • Building full-stack financial analysis tools with React, FastAPI, and Python-based quantitative models
  • Bridging academic research and practical applications in algorithmic trading systems
2024 - Present

Teaching Assistant & Student Assistant

Texas Tech University

  • Providing mathematics tutoring for undergraduate students across calculus, statistics, and linear algebra
  • Translating complex mathematical concepts into accessible explanations for diverse student populations
  • Managing departmental operations including scheduling, phone systems, and administrative coordination
  • Developing communication skills essential for client-facing quantitative finance roles

Technical Skills

Expertise spanning quantitative finance, machine learning, and full-stack development

Programming Languages

Python MATLAB JavaScript R C++

ML Frameworks

PyTorch TensorFlow Scikit-Learn XGBoost LightGBM Hugging Face

Financial Tools

QuantLib yfinance backtrader Bloomberg API ta-lib QuantConnect

Quantitative Methods

Time Series Analysis Monte Carlo Simulations Stochastic Calculus Statistical Arbitrage Factor Modeling Risk Management

ML Algorithms

LSTM Networks Random Forests Gradient Boosting SVMs Reinforcement Learning Transformers

Web Development

React FastAPI Flask REST APIs Docker AWS

Achievements & Recognition

Kaggle Competitions Expert Top 1% • Rank 1,237 of 201,885 • 1 Gold, 2 Bronze
Presidential Scholar Full PhD Funding • Texas Tech University
Research Impact 10 Publications • 32 Citations • H-Index: 4
DeepAI Finance Co-Founder AI-Powered Trading Systems in Real Markets

Get In Touch

Let's discuss opportunities in quantitative finance, research collaboration, or AI innovation

Email

akash404deep@gmail.com