I am a pursuing Master of Statistics from Indian Statistical Institute, Kolkata.
My research interests broadly revolve around Quantitative Trading, Deep Learning, Computer Vision, NLP and Quantum Computing. Recently, I have developed deep interest in Market Microstructure Modeling, Risk Management and financial application of Machine Learning models in Anti-Money Laundering and Fraud Detection.
I am actively looking for Internship Opportunities.
In my free time, I love to play cards and strategy games, travel and sketch. I enjoy writing about my experiences and ideas on Medium.
This is my go-to language at the moment. Have written several packages in Python.
Worked Extensively on Face Recognition, Object Detection and Image Segmentation
Worked extensively on Machine Translation, Document Representation and LLMs
Recently gained interest in this field. Working on Market Microstructure simulation.
Contributed to several research work towards improving fairness and performance of DL Systems
Contributed to Transpilation Methods for advancement of NISQ Quantum Hardware
Skilled in Implementation of several Advanced Data Structure and Algorithms
Skilled in Statistical Inference, Stochastic Processes and Learning Theory
Love solving puzzles and have exposure to Advanced Probability
My past work mostly include Quant Finance, Quantum Computing, Computer Vision, NLP and GenAI.
Contributed to Transaction Model Risk Management and Review. Streamlined and automated key components of the Model Review Workflow.
Contributed to Traspilation Methods for efficient and fast mapping of Program Quantum Circuit on Hardware Topology Circuit via Graph-Cutting Algorithms.
Responsibilities included:
Contributed towards Neural Face Recognition Robustness Research Paper. Contributed towards Biometric Capacity and Fairness of Deep FR Systems.
Responsibilities include:
Contributed toward Unsupervised Image Segmentation, Object Detection and Generative AI Research.
Responsibilities included:
Improved the existing system in production for annotating speech transcript data at scale and presented my work at IndoML23 Tutorial Session.
Recieved The Best Project Award at the School of AI and Data Science during my Summer Internship.
Best Report and Presentation of Data Analysis.
Events That Keep Me Up-to-Date
Arsenal of self-motivated past and present projects in AI, ML and Data Science, with their applications in NLP, CV, Computational Neuroscience and AI For Social Good
Unsupervised Topic Modelling technique for unsupervised product attribute extraction from Amazon India. We release two models - Fine-tuned Brand Name Detector and MLM on Product Data.
A Streamlit WebApp Multi-Armed Bandit Game with Epsilon Greedy Agent Simulation
Unofficial implementation to the paper - “Phase Transitions, Distance Functions, and Implicit Neural Representations” for 3D surface reconstruction based on point clouds
Exploring Parametrized Quantum Circuits for solving NP-Hard Travelling Salesman Optimization roblem with Variational Quantum Eigensolver
Designing a novel Contrastive Perturbative (CP) Framework for estimating adjustable perception-based weights for poverty indicators relevant for Indian context using Discrete Choice Models
Contextual Information-rich joint embedding for image and text in a multi-modal vector space using object-text collocation and Relative Position-based Transformer
Scanned Document Representation Learning using Image-Text-Loc Fusion CNN-Transformer and leveraging it for clustering and classification into 16 document categories
Explored several baseline Transformer models built from scratch for English to low-resourced North-Eastern Indian Languages in an effort to mainstream large native population
Psychological analysis of face recognition abilities and tendency among humans using survey and psychological techniques with categorical data analysis
Unraveled uncertainty as a major underlying latent variable for explaining emotional dynamics in the Brain, revealing significant represenational difference between age groups
R Shiny Webapp to conduct and provide dashboard results for Digit Span Psychology Test for measuring Short-Term Memory Capacity with detailed analysis of performance
Study on the pro-environmental attitude among college students of India and suggesting necessary measures leveraging statistical inference techniques.
Created a Webapp for generating global vector map by stitching local locations on map screenshots using Linear Statistical Model and also presenting residual analysis.
Devised new definition of model fairness based on Adversarial notion and implemented several fairness techniques like fairness regularization and LFR in NNs
Logistic Regression was used to identify genes responsible for Alzheimer’s Disease with high accuracy, sensitivity and specificity paired with great visualization
Implemented Expectation-Maximization Algorithm from scratch for image segmentation with Gaussian Mixture Model and its application to Brain Images and written notes
A fast video background subtraction that generates mask of moving foreground objects for surveillance videos using Kernel Density Estimation and thresholding
Eigenvalues and Eigenvector calculation of covariance matrix using several optimized iterative techniques with application to Principal Component Analysis
Air Quality Index data analysis during COVID-19 for 4 major Indian cities, including inference, modelling and investigation for drops in pollution.
Matrix Computations, Statistical Optimization and Physics simulation with advanced mathematical modelling techniques like Finite Elements Methods
Teaching is a Great Way to Keep Learning
Always Engaged in Learning and Achieving Milestones
Let’s build, research and collaborate.