Kishan Manani
Senior Data Scientist Machine Learning Engineer
London, England, United Kingdom
Summary
🤩
Rockstar🎓
Top SchoolKishan Manani is a Senior Data Scientist and Machine Learning Engineer based in London with over a decade of experience applying statistics and ML across finance, e-commerce, and healthcare, now leading ML efforts at Gucci. He has built and managed cross-functional teams that deliver end-to-end ML products—scalable forecasting, pricing optimisation, supply planning and automated experimentation—combining research rigor from a PhD in Physics with production engineering on Docker, Kubernetes and cloud platforms. An active open-source contributor to high-profile Python projects like statsmodels and sktime, he has implemented novel time-series methods (e.g., MSTL) and practical transformers that improve forecasting pipelines. His background in large-scale cardiac time-series analysis and published research gives him a rare blend of domain-science insight and hands-on production delivery. He also develops online courses and has a track record of translating complex models into business value and reproducible software.
8 years of coding experience
7 years of employment as a software developer
Doctor of Philosophy (Ph.D.) Physics, Doctor of Philosophy (Ph.D.) Physics at Imperial College London
Stackoverflow
161reputation
17kreached
0answers
2questions
Github Skills (18)
python10
data-science10
scikit10
pandas10
statistics10
machine-learning10
time-series10
econometrics10
forecasting10
sktime10
statsmodels10
scikit-learn10
forecast10
data-analysis10
regression-models9
Programming languages (4)
Github contributions (5)
sktime/sktime
Aug 2022 - Dec 2022
A unified framework for machine learning with time series
Role in this project:
Data Scientist
Data ScientistContributions:19 reviews, 9 commits, 10 PRs in 4 months
Contributions summary:Kishan primarily contributed to the `sktime` repository by addressing issues and enhancing the functionality of time series transformers and forecasters. They fixed a bug in the `DirectReductionForecaster` concerning exogenous variables and made column naming consistent in the `Lag` transformer. The user also implemented new features, such as the `TimeSince` transformer with options for numeric output and positive-only values, and added a multiplicative option to the `Detrender` transformer.
forecastingtime-series-analysistime-series-regressiondata-sciencedeep-learning
statsmodels/statsmodels
Feb 2022 - Apr 2022
Statsmodels: statistical modeling and econometrics in Python
Role in this project:Data Scientist
Data ScientistContributions:2 reviews, 16 commits, 11 PRs in 2 months
Contributions summary:Kishan primarily contributed to the statsmodels library by implementing and enhancing statistical modeling and econometrics tools. Their work included adding the "burg" method for partial autocorrelation calculations, fixing a Value Error issue with the `lagmat` function when dealing with pandas DataFrames, and introducing the MSTL method for time series decomposition. The user also added example notebooks, tests, and documentation to the project.
forecastingpythonregression-modelsstatsmodelsstatistics
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.