Anjum Sayed - Lead Data Scientist

Anjum Sayed

Lead Data Scientist

Stony Stratford, England, United Kingdom

Join Prog.AI to see contacts

Summary

👤

Senior

🎓

Top School

Anjum Sayed is a Lead Data Scientist with over a decade of cross-domain experience applying state-of-the-art deep learning and classical ML to energy, motorsport and finance problems. A former petrophysicist at bp, he built scalable automated workflows across upstream, downstream and renewables, often turning decades of messy data into production-ready models that drove measurable operational gains. Now at McLaren Racing he develops predictive tools that help win championships, while also founding Tapesearch to explore new data-driven ventures. A top-ranked competitive data scientist (multiple 1st and 2nd place finishes) he brings practical expertise in PyTorch, TensorFlow, XGBoost, RAPIDS and cloud ML, plus web and database skills to ship end-to-end solutions. He contributes to notable open-source projects—improving financial analytics in the ffn library and adding leakage-safe encoders to scikit-learn-contrib—demonstrating attention to robustness and reproducibility. His background in particle physics and field experience across challenging oilfields give him an uncommon blend of theoretical rigor and pragmatic engineering.

10 years of coding experience

3 years of employment as a software developer

University College London

Stackoverflow

Stats

884reputation

184kreached

15answers

10questions

Github Skills (22)

performance-monitor10

python10

scikit10

finance10

pandas10

numpy10

statistical-models10

cross-validation10

scikit-learn10

modeling10

metric10

data-analysis10

data-science9

machine-learning9

computer-engineering8

Programming languages (8)

TypeScriptC++CAstroLassoJavaScriptJupyter NotebookPython

Github contributions (5)

scikit-learn-contrib/category_encoders

Mar 2020 - Mar 2020

A library of sklearn compatible categorical variable encoders

Role in this project:

Data Scientist

Contributions:7 commits, 2 PRs, 7 comments in 21 days

Contributions summary:Anjum primarily contributed to the `category_encoders` library by adding a `NestedCVWrapper` class to prevent target leakage within supervised encoders. The user modified the code and documentation and implemented methods to ensure compatibility with the existing encoder structure. They also added unit tests, and ensured correct functionality with custom cross-validation methods.

sklearnsklearn-compatibleencodersvariablecategorical

pmorissette/ffn

May 2016 - May 2016

ffn - a financial function library for Python

Role in this project:

Back-end Developer / Data Scientist

Contributions:8 commits, 3 PRs, 1 comment in 1 day

Contributions summary:Anjum's primary contribution involves enhancing the `ffn` library with financial functions, specifically focusing on the implementation of Calmar and Sortino ratios. The commits demonstrate the addition of these performance metrics across daily, monthly, and yearly timeframes within the `PerformanceStats` class, showcasing a focus on financial analysis. The code modifications also incorporate bug fixes related to the calculation of downside risk and refine the organization of displayed statistics.

financialpythonfunction-libraryfinancial-dataquantitative-finance

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.

Request Free Trial