Jean-Michel Nairac, Developer in Grand Gaube, Rivière du Rempart District, Mauritius
Jean-Michel is available for hire
Hire Jean-Michel

Jean-Michel Nairac

Verified Expert  in Engineering

Data Scientist and Developer

Grand Gaube, Rivière du Rempart District, Mauritius

Toptal member since December 27, 2021

Bio

Jean-Michel is a senior data scientist and quantitative risk manager with 8+ years of experience. He worked at PwC and CIEL Group Companies, where he also gained his consulting experience, strong business acumen, and leadership skills. Jean-Michel's industry experience is backed by bachelor's degrees in economics and statistics and a master's degree in financial mathematics. He is currently ranked in the top 2% of Kaggle competitions.

Portfolio

CIEL Finance Data Services Ltd
Python, Pandas, Azure Computer Vision API, Azure Machine Learning, SQL, SQL...
Loop Shops Ltd (Self-employed)
PrestaShop, Web Hosting, CRM, Online Marketing, Supply Chain...
CIEL Corporate Services Ltd
Risk Management, Financial Risk Management, Operational Risk, Market Risk...

Experience

Availability

Part-time

Preferred Environment

Python, Microsoft Azure, Scikit-learn, LightGBM, XGBoost, TensorFlow, Pandas, NumPy, SQL

The most amazing...

...machine learning model I've built predicts the credit scores of loan applicants. I also designed the data pipeline to automate the loan approval process.

Work Experience

Lead Data Scientist

2020 - PRESENT
CIEL Finance Data Services Ltd
  • Built a machine learning model that predicts the credit scores of loan applicants for a bank.
  • Developed the model in Python with LightGBM, TensorFlow, scikit-learn, and Pandas and designed the data pipeline to automate the loan approval process in Microsoft Azure.
  • Built an anomaly detection tool that uses machine learning to automatically detect anomalies and data quality issues in bank transaction data. I developed this in Python with the PyOD package.
  • Used computer vision and optical character recognition in Microsoft Azure to extract electricity meter readings from security image capture.
  • Worked closely with clients to strengthen their understanding of data science, artificial intelligence, and machine learning to help them identify viable ML use cases for their businesses and present their business cases to C-level executives.
  • Collaborated with data engineers to understand data and data infrastructure requirements to put machine learning models into production for every use case. This involved daily standups and sprint planning using Jira.
Technologies: Python, Pandas, Azure Computer Vision API, Azure Machine Learning, SQL, SQL, Keras, Machine Learning, Deep Learning, Data Science, Predictive Analytics, Commercial Banking, Finance, Statistical Methods, Scikit-Learn, LightGBM, XGBoost, Anomaly Detection, Principal Component Analysis (PCA), Azure Data Factory, TensorFlow, Algorithms, Data Science, Data Analysis, Business Intelligence Development, Data Visualization, Dimensionality Reduction, Jira, Data Science, Leadership, CatBoost

Executive Director

2018 - 2021
Loop Shops Ltd (Self-employed)
  • Mastered PrestaShop and leveraged it to become an eCommerce developer and online marketing specialist.
  • Built an eCommerce website for selling organic food items locally in Mauritius (morganic.mu).
  • Gained entrepreneurial, sales, and CRM experience by creating this startup and building relationships with multiple local vendors.
Technologies: PrestaShop, Web Hosting, CRM, Online Marketing, Supply Chain, E-commerce marketing, Data Analysis, Data Science, Leadership, Design Directors

Head of Risk

2017 - 2020
CIEL Corporate Services Ltd
  • Built a financial risk model that quantified the organization's risk appetite. This included deriving the expected financial return for the organization and each of its subsidiaries.
  • Won the Best Risk Management Report award at the 2017 PwC Corporate Reporting Awards in Mauritius.
  • Designed and implemented an overall risk management process for the organization, which required expertise in healthcare, textiles, agriculture, finance, real estate, and hospitality.
  • Supervised and trained risk officers, built and presented reports to C-level executives and board members, and ran risk awareness campaigns for large audiences.
  • Supported the organization's risk management efforts through COVID-19 and developed and executed a pandemic response plan.
Technologies: Risk Management, Financial Risk Management, Operational Risk, Market Risk, Credit Risk, Financial Modeling, Data Science, Data Analysis, Data Science, Leadership

FX & Derivatives Trader

2016 - 2017
Afrasia Bank Ltd
  • Built a machine learning model in Python that predicts hourly foreign exchange fluctuations in the EUR/USD FX rate. I developed this model to showcase the power of machine learning and algorithmic trading for the bank.
  • Used technical and fundamental analysis to trade FX and FX derivatives at the treasury desk.
  • Designed FX-related structured products for clients.
Technologies: Forex Traders, Structured Products, Machine Learning, Python, Data Science, Data Analysis, Data Science, Algorithms

Data Scientist

2015 - 2015
DataProphet Ltd
  • Built an agent-lead matching model for call centers. We used a gradient boosting machine to predict which agents would be most suitable to handle call leads that yield the highest conversion rate built-in R with the GBM package.
  • Assisted the sales team in sourcing leads and onboarding clients with the benefit of CRM tools like Pipedrive.
  • Built machine learning models for debt collection and financial services companies built-in Python with scikit-learn.
Technologies: Python, R, Machine Learning, Data Science, CRM, Data Analysis, Data Science

Actuarial, Risk, and Quant Consultant

2013 - 2015
PwC
  • Applied financial engineering and quantitative finance techniques to build financial and credit risk models and value financial derivatives.
  • Valued and reviewed risk-weighted bank assets in accordance with Basel II and III. Consulted with major banking clients and reported and presented to C-level executives.
  • Performed actuarial reviews, including IAS 19 employee benefit reviews.
Technologies: Financial Modeling, Financial Engineering, Machine Learning, R, Python, SAS, SQL, Credit Risk, Market Risk, Risk Models, Data Science, Design Consulting, Basel II, Basel III, Asset Valuation, Data Science, Data Analysis, Data Science, Quantitative Analysis, Quantitative Development

Automation of Loan Approvals

OVERVIEW
A bank client engaged Ciel Finance Data Services Ltd to automate its loan application process, which was manual and tedious. Loans were pre-approved based on a simple checklist, and final approval was a qualitative exercise reviewed by multiple committees.

SOLUTION
1. Design a new loan application process.
2. Build ML models to produce a credit score for loan approval.

I designed a new data pipeline that involved:
• An ETL process of the data into Microsoft Azure.
• A Python script to execute the ML models and predict the credit scores.
• A SQL database to store the results and push them to the client via email.
• Azure Data Factory to orchestrate and automate the process.

I built two ML models and combined them to produce a credit score. One model predicts the probability that the committees will reject the application, and the other predicts the probability of default given that the committees approved the loans. Each model uses deep learning (TensorFlow and Keras), and gradient boosted trees (LightGBM and XGBoost). Features were engineered with statistical methods using Pandas, SciPy, and NumPy.

OUTCOME
We saved the bank a lot of time by discontinuing several committees and improving its loan default rate.

Anomaly Detection Tool for Bank Transactions

OVERVIEW
An anomaly detection tool I built to detect anomalies in bank transaction data. The tool is an ensemble machine learning model of many models with various hyperparameters of KNN, HBOS, Isolation Forest, PCA, and COPOD models.

CHALLENGE
The client did not have a system to detect anomalies, so they used only ad hoc samples.

SOLUTION
I engineered research-backed features for anomaly detection in bank transaction data. The data pipeline involves an ETL process of incrementally loading data into Microsoft Azure SQL Database using Azure Data Factory. A Python script containing the anomaly detection tool is automatically executed on the incrementally loaded data, and a CSV file containing anomalies is sent directly to the client by email.

OUTCOME
The client is using my anomaly detection tool because:
• It can run all transaction data as opposed to a sample.
• It automatically filters outliers, which is a vast improvement over the manual process.
• It provides an outlier score so that the client can prioritize the investigation of potential anomalies as they see fit.

The client confirmed that the tool is effective in detecting more data quality issues and fraudulent activities than the ad hoc sampling process.

Predicting Volatility for Options Trading

https://www.kaggle.com/nrcjea001/lgbm-baseline-no-leaks-stratifiedgroupkfold
OVERVIEW
This was a Kaggle competition to predict volatility for options trading.

CHALLENGE
We received trade data and order book data in 10-minute intervals per second, totaling over one billion data points. Our task was to predict 10-minute volatility with performance assessed using root mean squared percentage error (RMSPE) between true and predicted volatility.

SOLUTION
I performed well in this competition because I:
• Applied data analytics to correctly handle errors, such as trading halts, stock splits, mergers, and low trading volumes.
• Used the correct cross-validation technique (StratifiedGroupKFold).
• Engineered research-backed features (papers on algorithmic trading are freely available on Google Scholar and arXiv).
• Re-engineered timestamps and captured correlation between timestamps.
• Engineered features that correctly captured the correlation between stocks (Pandas and NumPy).
• Used ensemble methods of linear models (scikit-learn), gradient boosted trees (LightGBM), and deep learning (TensorFlow and Keras).

Computer Vision and OCR of Meter Readings

OVERVIEW
The client manually recorded electricity meter readings. This tedious process consumed a lot of the client's resources because many meter readings had to be recorded on a regular basis.

PROPOSAL
We proposed using security cameras to capture images and automatically extract the meter readings using artificial intelligence and machine learning.

SOLUTION
We used Microsoft Azure tools to build the solution and the custom vision software to detect objects—meter screens from security image captures. Microsoft also provides Computer Vision OCR for text extraction from images. We combined these into a SaaS solution to detect meter readings from security images.

The pipeline is engineered as follows:
1. The security image captures are uploaded to Azure Blob storage.
2. This triggers a Python script that makes an API call to the custom vision predictions and another API call to the Computer Vision OCR.
3. Meter readings are extracted and pushed to an Azure SQL database.

OUTCOME
The client saves a lot of time, and resources are freed up to focus on other tasks.
2012 - 2013

Master's Degree in Financial Mathematics

University of Cape Town - Cape Town, South Africa

2007 - 2011

Bachelor's Degree in Statistics

University of Cape Town - Cape Town, South Africa

2007 - 2010

Bachelor's Degree in Economics

University of Cape Town - Cape Town, South Africa

JUNE 2014 - PRESENT

Professional Risk Manager (PRM)

PRMIA

Libraries/APIs

Pandas, XGBoost, CatBoost, Scikit-Learn, Keras, TensorFlow, NumPy, Azure Computer Vision API, SciPy

Tools

PrestaShop, Business Intelligence Development, Azure Machine Learning, MATLAB, Jira

Frameworks

LightGBM

Languages

Python, R, SQL, SAS

Paradigms

Anomaly Detection, Quantitative Research

Platforms

CRM, Windows Development, Design Directors

Storage

SQL, Azure, Database, Azure

Other

Feature Engineering, Data Science, Data Science, Statistical Methods, Finance, Commercial Banking, Credit Risk, Operational Risk, Risk Management, Financial Risk Management, Financial Modeling, Financial Engineering, Risk Models, Data Science, Data Analysis, Dimensionality Reduction, Data Science, Quantitative Analysis, Model Validation, Machine Learning, Machine Learning, Principal Component Analysis (PCA), Predictive Analytics, Options Trading, Market Risk, Online Marketing, E-commerce marketing, Data Science, Time Series Analysis, Algorithms, Numerical Analysis, Variational Autoencoders, Azure Data Factory, Artificial Intelligence, OCR, Deep Learning, Web Hosting, Supply Chain, Forex Traders, Structured Products, Data Science, Econometrics, Asset Valuation, Mathematics, Statistics, Operations Research, Markov Chain Monte Carlo (MCMC) Algorithms, Generalized Linear Model (GLM), Numerical Methods, Probability Theory, Stochastic Process, Multivariate Statistical Modeling, Bayesian Statistics, Decision Modeling, Portfolio Analytics, Economics, International Trade, Macroeconomics, Microeconomics, Microsoft Azure, CRM, Design Consulting, Basel II, Basel III, Gradient Boosted Trees, Predictive Modeling, Computer Vision, Data Visualization, Algorithms, Backtesting Trading Strategies, Leadership, Quantitative Development

Collaboration That Works

How to Work with Toptal

Toptal matches you directly with global industry experts from our network in hours—not weeks or months.

1

Share your needs

Discuss your requirements and refine your scope in a call with a Toptal domain expert.
2

Choose your talent

Get a short list of expertly matched talent within 24 hours to review, interview, and choose from.
3

Start your risk-free talent trial

Work with your chosen talent on a trial basis for up to two weeks. Pay only if you decide to hire them.

Top talent is in high demand.

Start hiring