About Abhishek Tiwari

Professional Background

Applied optimization researcher and systems with a strong interest in simulation-based optimization, stochastic modeling, and large-scale decision systems. My recent work focuses on building interpretable, end-to-end optimization pipelines that integrate regime detection, simulation, and reinforcement learning techniques for real-time decision-making under uncertainty.

I designed and implemented a comprehensive Stochastic Portfolio Optimization Engine using Hidden Markov Models (HMMs) for regime detection and Monte Carlo simulation for dynamic allocation under uncertainty. While grounded in financial applications, the system architecture, optimization methodology, and simulation framework are domain-agnostic and extend naturally to logistics, energy systems, autonomous control, and healthcare optimization.

My core strengths lie in building simulation engines, formulating constrained optimization problems, and integrating learning-based components (RL, Bayesian inference, and deep models) into high-dimensional decision frameworks.

Technical Expertise

Programming & Tools

  • Languages: Python, R, SQL, C++
  • Libraries: NumPy, Pandas, SciPy, Scikit-learn, TensorFlow
  • Optimization & Simulation: Monte Carlo, Stochastic Programming, HMMs, MDPs, Simulation-based Optimization
  • Systems: PostgreSQL, MongoDB, InfluxDB, AWS, GCP

Applied Optimization & Simulation

  • Regime-Switching & Markov Decision Processes
  • Constrained Portfolio Optimization (Model-Agnostic Frameworks)
  • Monte Carlo Simulation for Dynamic Systems
  • Sensitivity & Robustness Analysis in Black-Box Models
  • Experimental Design for Simulation-Based Evaluation

Machine Learning

  • Time Series Modeling & Forecasting
  • Bayesian Inference (MCMC, Variational)
  • Deep Learning Models for Sequential Data
  • Probabilistic Modeling & Uncertainty Quantification

Contact Information