Publication
Optimizing Retailer Revenue With Sales Forecasting AI
https://www.toptal.com/developers/artificial-intelligence/retail-sales-forecasting-ai
Ahmed is available for hire
Hire AhmedAhmed Khaled
Verified Expert in Engineering
Data Science Developer
Cairo, Cairo Governorate, Egypt
Toptal member since March 23, 2020
Bio
Ahmed is an AI and data architect specializing in cloud migrations and AI-integrated data pipelines. He has a proven track record of replacing multi-million-dollar legacy software with agile, serverless designs. He led the end-to-end transformation of a legacy global platform into a centralized AWS-based solution for 30+ Pfizer manufacturing sites in just 1.5 years. He also managed a team of 10, delivering complex ETL pipelines, centralized data mapping, and manual data entry applications.
Portfolio
Pfizer - Manufacturing Operations Solutions
R, RStudio Shiny, RStudio, JavaScript, Applications...
SciMar One, LLC
Python, Azure, Version Control, APIs, Databases, MongoDB, SQL, Pyodbc, Async.js...
Freelance
Amazon Web Services (AWS), OpenCV, Natural Language Toolkit (NLTK), Keras...
Experience
- Python - 6 years
- Computer Vision - 5 years
- Deep Learning - 4 years
- Amazon Web Services (AWS) - 4 years
- Salesforce - 3 years
- Generative Pre-trained Transformers (GPT) - 2 years
- Business Process Optimization - 2 years
- Natural Language Processing (NLP) - 2 years
Preferred Environment
Data Science, Shell, Linux, Matplotlib, Plotly, Keras, PyTorch, TensorFlow, OpenCV, Docker
The most amazing...
...thing I've architected and delivered is AI and cloud migration for Pfizer in 18 months, replacing a $2 million-per-year legacy platform with an AWS ecosystem.
Work Experience
R Developer
2021 - PRESENT
Pfizer - Manufacturing Operations Solutions
- Developed an app that manipulates a secure database, with essential operations like creating, editing, and deleting records, an approval system and auditing, and Excel-like looks and feel; GMP validated and currently in production.
- Created an automated reporting application that takes certain input from users and can generate any of the four reports based on a template and dynamic data retrieved by user choice.
- Implemented an e-signature system in R Shiny using OAuth 2 mechanism.
Technologies: R, RStudio Shiny, RStudio, JavaScript, Applications, GNU Multiple Precision (GMP), Agile, Python, SAML-auth, OAuth 2, Data Science, Data-driven Decision-making, Decision Modeling, Decision Trees, Optical Character Recognition (OCR), API Integration, Supervised Machine Learning, Unsupervised Learning, MySQL, Data Analytics, Snowflake, Spotfire, Python 3, CSS, HTML, Dash, Google Colaboratory (Colab), Jupyter Notebook, LaTeX, Information Retrieval, Modeling, Large Language Models (LLMs), ChatGPT, Generative Artificial Intelligence (GenAI), Predictive Analytics, System Design, Fine-tuning, Dashboards, Reporting, Amazon S3 (AWS S3), FastAPI, Image Classification, AI Adoption, Strategy, PDF, API Design, Hugging Face Transformers, React
Python Back-end Developer
2021 - PRESENT
SciMar One, LLC
- Developed the core logic of the website back end using Python and hosted on Azure.
- Designed the database architecture for the website back end.
- Designed several Azure Logic apps for curation functionality.
Technologies: Python, Azure, Version Control, APIs, Databases, MongoDB, SQL, Pyodbc, Async.js, Web Scraping, Object-oriented Programming (OOP), Algorithms, Artificial Intelligence (AI), Amazon Web Services (AWS), PostgreSQL, Git, Data Science, Data Warehouse Design, Data Warehousing, AWS Lambda, Docker, GitHub, Linux, Optimization, Data Engineering, Time Series, Image Processing, Forecasting, Time Series Analysis, Neural Networks, Image Recognition, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Cloud Computing, Computer Vision Algorithms, Predictive Modeling, Optical Character Recognition (OCR), Team Leadership, API Integration, Machine Learning Operations (MLOps), Supervised Machine Learning, Unsupervised Learning, MySQL, Data Analytics, Text Classification, Python 3, Videos, Models, Scikit-learn, Dash, Google Colaboratory (Colab), eClinicalWorks, Jupyter Notebook, Electronic Health Records (EHR), Information Retrieval, ETL, Dashboards, Business Intelligence (BI), Reporting, Analytics, Amazon S3 (AWS S3), Image Classification, Open Neural Network Exchange (ONNX), PDF, Agentic AI, API Design, Hugging Face Transformers, Google Cloud Platform (GCP), OpenAI
Senior Data Scientist
2018 - PRESENT
Freelance
- Built a program that takes a lung CT scan as an input and gives back a numerical and visualization output of the detected nodules in the scan, along with a malignancy score on the nodule and patient level.
- Worked on dashboard creation, data visualizations, and storytelling using Tableau, linked to multiple data sources; these dashboards were built to communicate findings with technical and non-technical people.
- Developed a receipt Optical Character Recognition (OCR) and text classifier to categorize items within a receipt to various classes.
- Implemented a community detection algorithm for academic purposes to detect better design patterns for the UK railway stations.
- Designed and built a tremor classification model based on 3D gyroscope acceleration readings.
- Developed a snoring detection program for medical purposes using Amazon SageMaker.
- Built an ace percentage forecast model to forecast the number of aces made by a tennis player in ATP or WTP tournaments. It reached 0.4 total loss.
- Created, trained, and deployed a resume parser in Spanish and English using AWS instances.
- Devised a sentiment scoring model based on restaurant reviews with a Yelp dataset.
- Developed the RL agent based on deep q-learning to play Sichuan mahjong. Created a rule-based model to generate data acting as a starting point in Sichuan mahjong. Used SL to train on the generated data and then RL to enhance the performance.
Technologies: Amazon Web Services (AWS), OpenCV, Natural Language Toolkit (NLTK), Keras, Computer Vision, Data Analysis, TensorFlow, Data Science, Git, Jupyter, Pandas, Machine Learning, Writing & Editing, Generative Adversarial Networks (GANs), Business Process Optimization, Generative Pre-trained Transformers (GPT), Natural Language Processing (NLP), Artificial Intelligence (AI), Deep Learning, Tableau, R, Python, Algorithms, SQL, PostgreSQL, Data Warehouse Design, Data Warehousing, AWS Lambda, MongoDB, Docker, Azure, GitHub, Linux, Statistics, Optimization, Data Engineering, A/B Testing, Medical Imaging, Reinforcement Learning, Object-oriented Programming (OOP), Image Processing, Forecasting, Time Series Analysis, Neural Networks, Image Recognition, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Cloud Computing, Computer Vision Algorithms, Predictive Modeling, Amazon Machine Learning, Salesforce, GIS, Statistical Modeling, Statistical Analysis, JavaScript, Data-driven Decision-making, Decision Modeling, Decision Trees, Optical Character Recognition (OCR), Leadership, Speech Recognition, Team Leadership, API Integration, Machine Learning Operations (MLOps), Supervised Machine Learning, Unsupervised Learning, C++, MySQL, Data Analytics, Snowflake, Text Categorization, Hugging Face, Sentiment Analysis, Python 3, Videos, Models, Scikit-learn, Image Generation, Dash, Team Mentoring, Google Colaboratory (Colab), Jupyter Notebook, Electronic Health Records (EHR), Technical Design, Genetic Algorithms, Google Analytics, Information Retrieval, ETL, Hadoop, Modeling, Deep Reinforcement Learning, Decision Analysis, Speech-to-Text (STT), Google Speech API, LangChain, Large Language Models (LLMs), Retrieval-augmented Generation (RAG), Open-source LLMs, ChatGPT, Generative Artificial Intelligence (GenAI), Predictive Analytics, System Design, AI Agents, Fine-tuning, Dashboards, Business Intelligence (BI), Reporting, Analytics, Amazon S3 (AWS S3), Image Classification, Open Neural Network Exchange (ONNX), PDF, Agentic AI, Hugging Face Transformers, Google Cloud Platform (GCP), OpenAI
Computer Vision Expert for Traffic Solution
2022 - 2023
Route Konnect
- Developed an app that detects and tracks vehicles and provides insights and analysis they may require.
- Implemented a new tracker integrating movement- and visual-based trackers ByteTrack and ReID.
- Introduced a homography calculator based on point selection in Python.
Technologies: Computer Vision, Python, OpenCV, Hugging Face, Python 3, Videos, Models, Scikit-learn, Google Colaboratory (Colab), Jupyter Notebook, Modeling, Deep Reinforcement Learning, Fine-tuning, Amazon S3 (AWS S3), Image Classification, Open Neural Network Exchange (ONNX), Residual Neural Networks (ResNets), AI Adoption, PDF, Google Cloud Platform (GCP), OpenAI
Computer Vision/Deep Learning Engineer
2020 - 2021
Sports Vision Lab
- Developed a soccer field registration module using Synthetic edge map dataset creation.
- Created a Player detection and tracking module using Deep Sort and Yolo.
- Built a Jersey number recognition module using super-resolution gans and deep learning.
- Developed an unsupervised model to classify each player's team.
Technologies: Python, Deep Learning, Machine Learning, Computer Vision, Version Control, Tracking, OpenCV, PyTorch, TensorFlow, Keras, Algorithms, Artificial Intelligence (AI), Amazon Web Services (AWS), SQL, Git, Data Science, GitHub, Linux, Statistics, Optimization, Data Engineering, Object-oriented Programming (OOP), Image Processing, Forecasting, Neural Networks, Image Recognition, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Cloud Computing, Computer Vision Algorithms, Predictive Modeling, Data-driven Decision-making, Decision Modeling, Decision Trees, Optical Character Recognition (OCR), Leadership, Supervised Machine Learning, Unsupervised Learning, MySQL, Data Analytics, Amazon SageMaker, Hugging Face, Sentiment Analysis, Python 3, Videos, Models, Image Generation, Jupyter Notebook, Deep Reinforcement Learning, Image Classification, Open Neural Network Exchange (ONNX), PDF, Hugging Face Transformers
Data Scientist
2018 - 2019
Synapse Analytics
- Developed a cement market price daily forecasting, for a big cement firm, to reduce the loss of money between company and distributors, with ten days horizon; 91% of forecast values were within a 5% error margin.
- Implemented a store assortment forecast to forecast the weekly demand of products and give the best combination of products to get the highest revenue possible; 90% of forecasts were within a 5% error margin. Built on an AWS EC2 cloud instance.
- Developed a lot of presentations and dashboards for various projects using Superset, Tableau, and Plotly.
- Handled big databases, and maintained their structure, design, and data flow.
- Worked on a clinic recommendation system, along with a time series forecasting model to predict when will be the next visit for a patient.
Technologies: OpenCV, Keras, TensorFlow, Data Science, Git, Jupyter, Pandas, Machine Learning, Data Analysis, Data Visualization, Natural Language Processing (NLP), Generative Pre-trained Transformers (GPT), Computer Vision, Deep Learning, Tableau, R, Python, Algorithms, Artificial Intelligence (AI), Amazon Web Services (AWS), SQL, PostgreSQL, Data Warehousing, AWS Lambda, MongoDB, Docker, Azure, GitHub, Linux, Statistics, Optimization, Data Engineering, Medical Imaging, Object-oriented Programming (OOP), Image Processing, Forecasting, Time Series Analysis, Neural Networks, Image Recognition, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Computer Vision Algorithms, Predictive Modeling, Statistical Modeling, Statistical Analysis, Data-driven Decision-making, Decision Modeling, Decision Trees, Optical Character Recognition (OCR), Speech Recognition, API Integration, Machine Learning Operations (MLOps), Supervised Machine Learning, Unsupervised Learning, MySQL, Data Analytics, Amazon SageMaker, Text Classification, Text Categorization, Sentiment Analysis, Python 3, Videos, Models, Image Generation, Dash, Jupyter Notebook, Hadoop, Modeling, Speech-to-Text (STT), Google Speech API, AI Agents, Business Intelligence (BI), Image Classification, PDF
Experience
Simple EDA on Gun Usage Data Along with Census Data in the US
This exploratory data analysis was done to study the relationship between the census data and the portions of the population in the US who uses guns to get insights among them and try to prevent or reduce this usage in the future.
Soccer Field Registration and Broadcast Analysis
Designing and implementing a pipeline that takes a broadcast and performs:
• Soccer edge detection
• Player detection and tracking (with occlusion handling)
• Jersey number recognition
• Homography extraction (player mapping on the minimap)
• Player team classification
• Ball detection and mapping
• Homography sequence stutter removal using convex optimization
All of it was done in Python, with free-custom-made datasets.
• Soccer edge detection
• Player detection and tracking (with occlusion handling)
• Jersey number recognition
• Homography extraction (player mapping on the minimap)
• Player team classification
• Ball detection and mapping
• Homography sequence stutter removal using convex optimization
All of it was done in Python, with free-custom-made datasets.
Arabic Sentiment Analysis
This project aimed to retrieve the sentiment of an Arabic sentence scraped from Twitter regarding multiple subjects. The first trial was on COVID-19 related tweets, and then it was employed on other material like sports.
Education
2013 - 2018
Bachelor's Degree in Biomedical and Systems Engineering
Cairo University - Cairo, Egypt
Skills
Libraries/APIs
Pandas, Matplotlib, TensorFlow, Keras, PyTorch, Natural Language Toolkit (NLTK), OpenCV, Scikit-learn, Hugging Face Transformers, OpenAI API, React, Pyodbc, GNU Multiple Precision (GMP), Google Speech API
Tools
Jupyter, Plotly, Google Analytics, Tableau, Git, LaTeX, Amazon SageMaker, Open Neural Network Exchange (ONNX), GIS, Spotfire, ChatGPT, GitHub, Shell, eClinicalWorks
Languages
Python, R, SQL, Python 3, Java, C++, Snowflake, CSS, HTML, JavaScript
Frameworks
RStudio Shiny, Spark, Hadoop, OAuth 2
Paradigms
ETL, Object-oriented Programming (OOP), Business Intelligence (BI), Agile
Platforms
Jupyter Notebook, Amazon Web Services (AWS), RStudio, Google Cloud Platform (GCP), AWS Lambda, Azure, Docker, Salesforce, Linux
Storage
PostgreSQL, Databases, MySQL, Amazon S3 (AWS S3), MongoDB, Elasticsearch, Apache Hive
Industry Expertise
Teaching, Bioinformatics
Other
Artificial Intelligence (AI), Time Series Analysis, Modeling, Statistics, Data Engineering, Image Processing, Algorithms, Deep Learning, Machine Learning, Computer Vision, Natural Language Processing (NLP), Business Process Optimization, Time Series, Medical Imaging, Data Visualization, Optimization, A/B Testing, EDA, Forecasting, Reinforcement Learning, Deep Reinforcement Learning, EMR, Biomedical Skills, Data Science, Data Analysis, Tracking, Deployment, Version Control, APIs, Neural Networks, Image Recognition, Deep Neural Networks (DNNs), Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Cloud Computing, Computer Vision Algorithms, Predictive Modeling, Amazon Machine Learning, Text Classification, Text Categorization, Optical Character Recognition (OCR), Supervised Machine Learning, Unsupervised Learning, Data Analytics, Generative Pre-trained Transformers (GPT), Hugging Face, Sentiment Analysis, Videos, Models, Dash, Google Colaboratory (Colab), LangChain, Predictive Analytics, Fine-tuning, Reporting, Image Classification, AI Adoption, Strategy, PDF, Agentic AI, OpenAI, Big Data, Technical Design, Data Warehouse Design, Generative Adversarial Networks (GANs), Data Warehousing, Genetic Algorithms, Decision Analysis, Electronic Health Records (EHR), Information Retrieval, Probabilistic Information Retrieval, Statistical Modeling, Statistical Analysis, Data-driven Decision-making, Decision Modeling, Decision Trees, Leadership, Team Leadership, API Integration, Machine Learning Operations (MLOps), Image Generation, Team Mentoring, Speech-to-Text (STT), Large Language Models (LLMs), Retrieval-augmented Generation (RAG), Open-source LLMs, Generative Artificial Intelligence (GenAI), System Design, AI Agents, Dashboards, Analytics, FastAPI, Residual Neural Networks (ResNets), API Design, Writing & Editing, Real-time Data, Integration, Async.js, Web Scraping, BERT, Applications, SAML-auth, Speech Recognition
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