Boris Banushev
Data Scientist
Singapore
Summary
🤩
Rockstar🎓
Top SchoolBoris Banushev is a data scientist and AI/quant specialist with eight years of experience building production-grade ML systems for financial services and startups from Singapore. He blends academic rigor—MSc in Data Science from UC Berkeley, MSc Finance, and an Oxford Economics PhD candidacy—with hands-on engineering at AWS, Databricks and HSBC, delivering solutions that span ML infrastructure, model fine-tuning and quant trading research. At thaita.app he engineered end-to-end pre-training and RLHF workflows for custom LLMs on proprietary options strategies, scaling agentic trading pipelines into production for hundreds of users. Comfortable across the stack, he integrates vector DBs, RAG, vLLM, RL frameworks and orchestration tools to turn research signals into automated execution. Known for fast learning and strong communication, he bridges quant research, software engineering and product to unlock alpha in real-time systems. Outside work he plays ice hockey—an unexpected indicator of his team-first, competitive drive.
8 years of coding experience
8 years of employment as a software developer
Doctor of Philosophy - PhD Economics, Doctor of Philosophy - PhD Economics at University of OxfordMaster's degree Global Business Analysis, Master's degree Global Business Analysis at Alliance Manchester Business School
Stackoverflow
31reputation
7kreached
1answer
0questions
Github Skills (22)
convolutional-neural-networks10
time-series10
recurrent-neural-networks10
discriminator10
generative-adversarial-network10
lstm10
databricks-industry-solutions8
aws-glue6
aws-cli6
machine-learning6
amazon-eks6
fsi5
sagemaker4
keras4
dlt3
Programming languages (4)
Github contributions (5)
borisbanushev/stockpredictionai
Jan 2019 - Feb 2019
In this noteboook I will create a complete process for predicting stock price movements. Follow along and we will achieve some pretty good results. For that purpose we will use a Generative Adversarial Network (GAN) with LSTM, a type of Recurrent Neural Network, as generator, and a Convolutional Neural Network, CNN, as a discriminator. We use LSTM for the obvious reason that we are trying to predict time series data. Why we use GAN and specifically CNN as a discriminator? That is a good question: there are special sections on that later.
Contributions:26 commits, 18 pushes, 1 branch in 1 month
convolutional-neural-networksdiscriminatorgenerative-adversarial-networklstmrecurrent-neural-networks
borisbanushev/anomaliesinoptions
Feb 2019 - Feb 2019
In this notebook we will explore a machine learning approach to find anomalies in stock options pricing.
Contributions:9 commits, 6 pushes, 1 branch in 1 day
machine-learning
Find and Hire Top DevelopersWe’ve analyzed the programming source code of over 60 million software developers on GitHub and scored them by 50,000 skills. Sign-up on Prog,AI to search for software developers.