RAHUL ANANTMathematics & Computing
Computational Research Profile

Research & Scientific Inquiries

Bridging rigorous mathematical foundations with modern computational architectures to address heritage preservation and financial market microstructure.

Focus Areas

Primary Research Interests

Document Epigraphy & Vision Transformers

Degraded historical character segmentation, morphological noise reduction, and transformer-based OCR for Indic palm leaves.

Market Microstructure & Order Book Dynamics

Deterministic sub-microsecond limit order execution, memory arena pools, and stochastic Hawkes processes.

Computational Finance & Stochastic Volatility

Antithetic Monte Carlo option pricing, Heston stochastic volatility surfaces, and Greek sensitivity risk metrics.

Parameter-Efficient LLM Fine-Tuning (PEFT / LoRA)

Low-rank adaptation architectures for domain-specific algorithmic problem solving and technical evaluation.

Investigations

Active & Completed Research Projects

Quantitative Finance & SystemsStatus: Under Review

Limit Order Book Engine: Market Microstructure Simulation

Implemented a limit order book matching engine with price-time priority (FIFO) and real-time depth tracking in Python and C++ to model core quantitative trading infrastructure and order flow dynamics.

Methodology

Built deterministic FIFO order matching, real-time book depth tracking, and order flow imbalance (OFI) metrics across tick-level simulation streams.

Dataset

Synthetic Poisson order streams and financial tick data.

Architecture & Models

FIFO Matching Engine, Order Flow Imbalance (OFI), Price-Time Priority Model

Outcome: Accurate reconstruction of market depth and microprice dynamics for algorithmic strategy analysis.

Empirical Simulation Plots & Performance Figures:

LOB Strategy Equity Curves

Cumulative Equity Curves under RECIM Transaction Friction

PnL Distributions

High-Frequency Trade PnL & Drawdown Distributions

Applied Machine Learning & EconomicsStatus: In Progress

Mineral to Memory: Applied Machine Learning Research

Ongoing machine learning research on Mineral to Memory under the supervision of Prof. Baijnath Kaushik, analyzing upstream mineral price shocks and downstream transmission dynamics.

Prof. Baijnath Kaushik (Head, School of Computer Science & Engineering)

Methodology

Assembling trade and commodity price time series, applying machine learning models to detect lead-lag transmission dynamics across supply dependencies.

Dataset

Mineral commodity price series and trade benchmarks.

Architecture & Models

Time Series Models, Machine Learning Regressors

Outcome: Ongoing faculty-supervised investigation into supply shock propagation.

Interested in Research Collaboration?

I welcome research inquiries, graduate lab discussions, and co-authorship proposals in deep learning vision systems and quantitative financial architectures.