Bilal Mahmood, Developer in Bergen, Norway
Bilal is available for hire
Hire Bilal

Bilal Mahmood

Verified Expert  in Engineering

Bio

Bilal is an experienced data scientist with solid knowledge of machine learning, data analysis, and visualization. He offers four years of professional experience in data science, working on projects related to building and deploying machine learning models, extracting insights from data, and managing data. Bilal is passionate about working with teams whose vision aligns with his values and specializations.

Portfolio

TV2.no
Python, LLM, Supervised Machine Learning, ChatGPT Prompts, ChatGPT
Gruber Logistics
Python, Azure Design, Data Science, Database, Teamwork, Data Modeling
Datatellers
Python, Pandas, NumPy, Data Science, Jupyter Notebook, AWS, Data Science...

Experience

Availability

Full-time

Preferred Environment

Ubuntu, Visual Studio Code (VS Code), Jupyter Notebook, Slack, Anaconda, Python, Gmail, R

The most amazing...

...thing I've worked on is prototyping an insurance recommender system for an Italian bank to improve its insurance marketing strategy.

Work Experience

Researcher

2024 - PRESENT
TV2.no
  • Prototyped a related news article recommender system that achieved a Recall@5 score of more than 50% as evaluated from the perspective of journalists and published the results at the RecSys 2024 workshop conference.
  • Used the machine learning ecosystem in Python to accomplish this prototype.
  • Involved in building an AI tool for journalists to find related articles quickly and publish them on the news website.
  • Employed state-of-the-art large language models to accomplish this task.
Technologies: Python, LLM, Supervised Machine Learning, ChatGPT Prompts, ChatGPT

Data Analyst

2022 - 2022
Gruber Logistics
  • Built, using an ML stack, an automated fuel event detection system from sensor data generated from hundreds of trucks and deployed it on the Spark cluster to speed up the management of fueling activities of the trucks.
  • Contributed to the data product that ran daily, detected all the fueling events of hundreds of trucks, and stored the results in the MongoDB database. The app gave the reporting team a heads-up about the number of payments to be expected from the fuel suppliers.
  • Worked on this data app that also gave potential measurements about the fueling activities of the trucks to detect if there was potential fueling fraud happening.
Technologies: Python, Azure Design, Data Science, Database, Teamwork, Data Modeling

Python Software Developer

2021 - 2021
Datatellers
  • Translated complex credit scoring model, which measured loan worthiness of customers, into Python code.
  • Deployed it as AWS Lambda function and exposed it as a REST API endpoint, using AWS API gateway, to be consumed by the front-end team to display customer ratings.
  • Worked with modular and efficient code in the speed of NumPy and the size of 250MB of the layer limitation.
Technologies: Python, Pandas, NumPy, Data Science, Jupyter Notebook, AWS, Data Science, Version Control Systems, Communication Coaching, Models, Predictive Modeling, Data Science, Database, PDF Scraping, Teamwork, Data Modeling

Consultant Data Scientist

2019 - 2020
Sparkasse | Cassa di Risparmio di Bolzano
  • Prototyped an insurance recommender system using machine learning classifiers that accurately and transparently ranked customers to be targeted with property, disease, accident, and legal insurance.
  • Trained several supervised machine learning classifiers using the Tree-based Pipeline Optimization framework and selected the best explainable model using the cross-validation technique, where the AUC score was the optimized metric.
  • Transferred machine learning methodology to the Sparkasse team by guiding them on essential steps required to build ML models, from data preprocessing to feature engineering, feature selection, model building, and finally, model evaluation.
  • Produced a detailed research report at the end of the project to communicate the critical findings at each level of the model-building process.
  • Deployed the model building and inference pipelines in the Konstanz Information Miner framework for transparency and a better understanding of the Sparkasse team.
Technologies: Data Analysis, Data Visualization, Recommendation Systems, AutoML, KNIME, Python, Artificial Intelligence, Modeling, Data Science, Version Control Systems, Communication Coaching, Models, Supervised Machine Learning, Predictive Modeling, Data Science, Database, Supervised Learning, Classifier Development, Teamwork, Data Modeling

Data Analyst

2017 - 2017
ibex
  • Built a multiclass ML model for AT&T and Frontier campaigns that detected customer issues from the transcribed calls with more than 75% accuracy, providing insights into the customer's main pain points.
  • Used Python's NLTK package and Stanford's NLP framework to identify customer sentiments about AT&T, Frontier, and Lyft clients and tracked them weekly in the form of Excel reports.
  • Managed exploratory data analysis to recommend new benchmarks for customer satisfaction and handling time for new agents to help them become more proficient without too much pressure.
Technologies: Data Science, Python, Generative Pre-trained Transformers (GPT), NLP, Machine Learning, Artificial Intelligence, Modeling, Data Science, Version Control Systems, Communication Coaching, Models, XGBoost, Predictive Modeling, Data Science, Database, Web Scraping, Supervised Learning, Classifier Development, Teamwork, Data Modeling

COVID-19 X-ray Classifier

https://github.com/bilalmahmood1/Covid-Detector
Built a deep-learning-based image classification model using transfer learning to measure whether X-ray images belong to COVID-19 patients. The project was part of my master's course. The model showed high accuracy on the validation set.

Insurance Recommender System for a Commercial Bank

I created a prototype for an insurance recommender system using machine learning classifiers that accurately and transparently ranked customers to be targeted with property, disease, accident, and legal insurance.

RESPONSIBILITIES
• Trained several supervised machine learning classifiers using the Tree-based Pipeline Optimization framework and selected the best explainable model using the cross-validation technique, where the AUC score was the optimized metric.

• Transferred machine learning methodology to the Sparkasse team by guiding them on the essential steps required to build ML models, from data preprocessing to feature engineering, feature selection, model building, and model evaluation.

• Produced a detailed research report at the end of the project to communicate the critical findings at each level of the model-building process.

• Deployed the model building and inference pipelines in the Konstanz Information Miner framework for transparency and a better understanding of the Sparkasse team.

Loan Credit Rating for SMEs

I translated a complex credit score rating algorithm (for a client for a client, more information at the link below) that measured the loan worthiness of different customers into efficient Python code and deployed it as an AWS Lambda function. It was exposed with a REST API endpoint to be consumed by the front-end team to display the ratings.

I also orchestrated the rating calculation using AWS Step Functions. When customers upload their financial documents into the S3 bucket, that event triggers the parsing of the files. It then prepares the data consumed by the rating calculation endpoint, which stores the results in the DynamoDB database.

URL: https://fdg.mcc.it/rating
2023 - 2024

Ph.D. in Artificial Intelligence

University of Bergen - Bergen, Norway

2018 - 2022

Master's Degree in Computer Science

Free University of Bozen-Bolzano - Bolzano, Italy

2010 - 2015

Bachelor's Degree in Electrical Engineering

Lahore University of Management Sciences - Lahore, Pakistan

FEBRUARY 2018 - PRESENT

Deep Learning Specialization

Coursera

SEPTEMBER 2016 - PRESENT

Data Analyst Nanodegree

Udacity

Libraries/APIs

Pandas, XGBoost, OpenAI Assistants API, NumPy

Tools

AutoML, Slack Development, Business Intelligence Development, ChatGPT

Languages

Python, SQL, R

Platforms

Visual Studio Development, Jupyter Notebook, Ubuntu, Data Science, AWS, KNIME, Azure Design

Storage

Database, PostgreSQL, NoSQL

Other

Machine Learning, NLP, Artificial Intelligence, Data Science, Data Science, Supervised Learning, LLM, Deep Learning, Data Visualization, Data Analysis, Statistics, Supervised Machine Learning, Image Recognition, Modeling, Version Control Systems, Communication Coaching, Models, Predictive Modeling, Generative Pre-trained Transformers (GPT), Classifier Development, Teamwork, Data Modeling, Mathematics, Engineering, Recommendation Systems, Gmail, OpenAI GPT-3 API, Chatbot Development, GPT-3, PDF Scraping, Web Scraping, Computer Vision, ChatGPT Prompts

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