You will get a clean analysis-ready dataset with full documentation
Project details
Most data analysts skip straight to charts and dashboards without fixing what is underneath. Bad data in means bad insights out no matter how good the visualization looks.
I clean data the way an ML engineer would. Not just removing blanks, but thinking about what the data needs to actually be useful downstream correct types, consistent formatting, outlier treatment, and a full log of every change made so you know exactly what was done and why.
I have cleaned datasets ranging from 1,000 to 100,000+ records across e-commerce, telecom, real estate, and customer analytics including a 20,770-record Airbnb NYC dataset with missing values, duplicates, type errors, and extreme price outliers, all documented and resolved.
You get back a clean file plus a transformation log not just a fixed dataset but a clear record of every issue found and every action taken.
I clean data the way an ML engineer would. Not just removing blanks, but thinking about what the data needs to actually be useful downstream correct types, consistent formatting, outlier treatment, and a full log of every change made so you know exactly what was done and why.
I have cleaned datasets ranging from 1,000 to 100,000+ records across e-commerce, telecom, real estate, and customer analytics including a 20,770-record Airbnb NYC dataset with missing values, duplicates, type errors, and extreme price outliers, all documented and resolved.
You get back a clean file plus a transformation log not just a fixed dataset but a clear record of every issue found and every action taken.
Data Tool
PythonWhat's included
| Service Tiers |
Starter
$40
|
Standard
$85
|
Advanced
$155
|
|---|---|---|---|
| Delivery Time | 2 days | 3 days | 6 days |
Number of Revisions | 1 | 2 | 3 |
Number of Pages Mined/Scraped | 0 | 0 | 0 |
Number of Sources Mined/Scraped | 1 | 2 | 3 |
Optional add-ons
You can add these on the next page.
Additional Revision
+$20
EDA report on cleaned data
(+ 2 Days)
+$35Frequently asked questions
About M Wajeeh
ML Engineer | Python | Predictive Modeling | Data Analytics
Islamabad, Pakistan - 8:25 pm local time
I help startups, students, and small teams build practical machine learning and data analytics solutions, from cleaning messy datasets and training models to building dashboards and deploying ML APIs.
My strongest areas are machine learning model development, predictive modeling, data preprocessing, and turning raw data into useful business insights. I also have hands-on experience with FastAPI, Docker, MLflow, DVC, and basic MLOps workflows, so I can help make ML projects more structured, reproducible, and easier to use beyond a notebook.
What I can help you with:
🧠 Machine Learning & Predictive Modeling
- Classification and regression models using Scikit-learn, XGBoost, TensorFlow, and PyTorch
- Data cleaning, preprocessing, feature engineering, and model evaluation
- Model performance improvement using proper metrics, validation, and experimentation
- End-to-end ML workflows from raw data to trained model
🚀 ML Deployment & Workflow Automation
- FastAPI-based machine learning APIs
- Dockerized ML applications
- Experiment tracking with MLflow
- Data/model versioning with DVC
- Clean project structure, documentation, and reproducible code
📊 Data Analytics & Dashboards
- Power BI and Tableau dashboards
- SQL analysis using joins, CTEs, window functions, and subqueries
- Python-based EDA, data cleaning, and reporting
- Business-ready insights for non-technical stakeholders
🤖 Generative AI Exposure
I have also worked with beginner-to-intermediate Generative AI and RAG concepts using LangChain, ChromaDB, and LLM APIs. I can help with document-based Q&A prototypes, semantic search, and AI feature experimentation.
📌 Selected Projects:
- PurchasePulse: XGBoost purchase intent model with 90.23% accuracy and 0.89 ROC-AUC, served through FastAPI with Docker and DVC
- Telco ChurnGuard: Customer churn prediction pipeline with 85% accuracy, CI/CD using GitHub Actions, and batch prediction workflow
- RAG Insight Engine: Document-based Q&A prototype using LangChain and ChromaDB with citation support
- E-Commerce SQL Analysis: 99,000+ orders analyzed in BigQuery to extract customer and sales insights
- Power BI Sales Dashboard: 5-year retail analysis with product, regional, and revenue insights
🛠️ Core Stack:
Python | Scikit-learn | XGBoost | TensorFlow | PyTorch | FastAPI | Docker | MLflow | DVC | SQL | BigQuery | PostgreSQL | Power BI | Tableau | GitHub Actions | LangChain | ChromaDB
✅ Why work with me:
- Winner of Vyrothon 2026 AI Hackathon among 580+ applicants
- Oracle Certified Generative AI Professional
- AI graduate with hands-on ML, analytics, and deployment project experience
- Clear communication, clean documentation, and structured delivery
- I focus on practical solutions, not just experimental notebooks
Best fit projects:
- Machine learning model training
- Predictive analytics
- Data cleaning and EDA
- Power BI/Tableau dashboards
- ML API deployment with FastAPI
- Beginner-to-intermediate AI/GenAI prototypes
If your project involves machine learning, data analytics, or making an ML model usable in a real workflow, send me a message and I’ll honestly tell you how I can help.
Steps for completing your project
After purchasing the project, send requirements so M Wajeeh can start the project.
Delivery time starts when M Wajeeh receives requirements from you.
M Wajeeh works on your project following the steps below.
Revisions may occur after the delivery date.
Dataset review and issue assessment
I open your file, profile the data, and document every quality issue found nulls, duplicates, wrong types, outliers before touching anything.
Cleaning and transformation
I fix all issues systematically and log every change made what was found, what action was taken, and how many rows were affected.