Hello, I'm
Ankit Singh
|
Data Scientist with a PhD in Physics — applying machine learning, statistical modeling, and large-scale data pipelines to both industry and research problems.
Hello, I'm
Data Scientist with a PhD in Physics — applying machine learning, statistical modeling, and large-scale data pipelines to both industry and research problems.
I build machine learning models, data pipelines, and deployed applications across domains — from classifying 151K road accidents and optimizing traffic signals with reinforcement learning, to RAG chatbots and quantitative finance toolkits. My PhD in Physics and 10+ years of research gave me deep experience with terabyte-scale datasets, statistical modeling, and HPC — skills that transfer directly to data science at scale.
Currently a Research Fellow at the University of Nottingham, I also hold two applied data science certifications from WorldQuant University (ML/CV and Applied DS) and have authored 12 peer-reviewed publications with 100+ citations.
Dual-strategy ML system on 151K UK road accidents: emergency response model achieving 92.4% severe recall and traffic management model with 81% macro recall using SMOTE+Tomek and ADASYN.
RAG chatbot using FAISS/ChromaDB vector stores and sentence-transformers to answer UK immigration questions from GOV.UK data.
Deep RL agent trained on real Transport for London API traffic flow data to learn adaptive signal timing policies for a single intersection, replacing fixed-cycle control.