Keval sakhiya

I am a Data Scientist and Data Engineer with over five years of experience in Python, data analytics, and machine learning. I specialize in building data pipelines, deploying scalable machine learning models, and solving real-world problems using AI. I have extensive experience with tools like TensorFlow, Scikit-learn, and cloud platforms like AWS and GCP. As a freelancer, I work on a variety of projects, delivering end-to-end solutions that transform data into actionable insights for clients across multiple industries.

Role
Python
Years of Experience
5.2 years
Professional Portfolio
View here

Skillsets

JavaScript
XgBoost
TensorFlow - 1 Years
SQL
Selenium
Scrapy
Scikit-learn
Requests
Python - 6 Years
PowerBI
NO SQL
Natural Language Processing
MLFlow - 2 Years
Keras
AWS
Google Cloud Platform
Git
Git
FastAPI
ETL
DVC
Docker
Django
Deep Learning
Data Pipelines
Data Analysis
Azure
AWS

Professional Summary

5.2Years

Jan, 2022 - Present3 yr 6 months
Data Scientist
Upwork

Applications & Tools Known

Keras
Scikit-learn
XGBoost
Power BI
AWS EC2
AWS S3
Azure
Google Cloud Platform
Git
Docker
MLflow
DVC
FastAPI
Django
ETL
Data Pipelines
Scrapy
Requests
Selenium
Power BI
SQL
NoSQL
AWS
MLflow
DVC
ETL
Data Pipelines
Requests
XGBoost
Power BI
SQL
AWS EC2
AWS S3
MLflow
DVC
ETL
Requests
NLP

Work History

5.2Years

Data Scientist

Upwork

Jan, 2022 - Present3 yr 6 months

Designed and implemented machine learning and deep learning models for diverse projects. Applied MLOps best practices by integrating data version control and Git, ensuring the reproducibility and scalability of models. Implemented experiment tracking using MLflow and set up CI/CD pipelines with Git Actions to streamline model deployment.

Major Projects

3Projects

Emotion Detection Using CNN

Developed a deep learning model using a Convolutional Neural Network (CNN) based on the ResNet architecture to detect and classify human emotions from images. Achieved high accuracy through extensive data preprocessing and model tuning.

Property Scout - Real Estate Price Prediction

Created a comprehensive real estate property price prediction system using XGBoost. The project includes a property recommendation system leveraging cosine similarity for location, facilities, and price, with a focus on MLOps practices including data version control and experiment tracking.

Movie Recommender System

Implemented a content-based movie recommender system that suggests movies to users based on their preferences. Utilized natural language processing (NLP) techniques to analyze movie metadata and calculate similarities using cosine distance, providing personalized recommendations.