Hello!

I'm Dhrumil Patel



A Junior Data Scientist

LinkedIn My works

Name: Dhrumil Patel

Job Role: Junior Data Scientist

Experience: 10 Months

Address: Gujarat, India

Skills

MySQL 60%
PYTHON 65%
MS Excel 70%
PowerBI 50%
Machine Learning 50%
Pdf Extraction- OCR(Regex),LLM 70%
Image Deblurring 55%
Django 50%

About

About Me

BE in Computer Engineering (June 2020 – May 2024) graduate with hands-on experience in Python, Django, and data science. Completed internships at CreArt Solutions, where I developed an E-noticeboard and a NGO website using Django. Enhanced my skills through the Fly the Nest Data Science program, gaining proficiency in Python, Excel, MySQL, Machine Learning, and Power BI. Currently a Junior Data Scientist at Deets Digital, working on computer vision technologies like PaddleOCR and Tesseract OCR for PDF text extraction & GenAI technologies like Chatbots on the Financial Datasets, Automated Loan Scores Generation and Financials-PDF extraction. Additionally, contributing to a research paper analyzing the adoption of new courses in Indian universities.

Dhrumil Patel is a Data Scientist and Data Analyst from India specializing in Python, SQL, Excel, Power BI, OCR, GenAI, and Machine Learning. This portfolio showcases projects, resume, and professional experience.

  • Profile: Data Science & Analytics
  • Education: Bachelor of Engineering- Computer Engineer
  • Programming Language: Python
  • Web Technologies: HTML, CSS, Bootstrap, Django
  • GenAI Technologies: LLMs - Gemini, GPT, Claude (For PDFs data extraction), Chatbots on the Financial Datasets
  • Data Analysis Technologies: PowerBI, MS Excel, Pandas, Numpy, MySQL
  • Visualization Technologies: Matplotlib, Seaborn, Excel charts, PowerBI charts
  • Computer Vision(OCR) Technology: PaddleOCR, Tesseract, EasyOCR, docTR
  • Tools/Software: Visual Studio, Sublime Text, Jupyter Notebook

Resume

Resume

Resume

Currently working as a Trainee at Deets Digital since August, gaining hands-on experience with computer vision technologies such as PaddleOCR and Tesseract OCR for text extraction from PDFs. Alongside this, I am actively working on a research paper focused on analyzing the adoption of new courses across Indian universities using data analysis techniques learned during the Data Science program. Passionate about combining software development and data science to build data-driven solutions for real-world problems.

Experience


May,2026- Present

Junior Data Scientist

Deets Digital

My role involves extracting necessary data fields from PDF documents and converting them into structured JSON outputs.

  • Implemented Optical Character Recognition (OCR) using Tesseract OCR, PaddleOCR, docTR for the Pdf text extraction & Handwritten Text extraction.
  • Used OpenCV (cv2) for image preprocessing — improving OCR accuracy by handling issues like blur, low resolution and skewed text.
  • Extracted necessary data fields from PDFs and converted them into structured JSON outputs with accuracy and efficiency
  • Implemented Large language model(LLM) using Gemini 2.5 flash,Claude Opus/Sonnet, GPT llms for data extraction.
  • Generated Chatbots using Pandas and Paid LLms on Financial Datasets.
  • Developed different automated loan scores for the financial datas.

Aug,2025- May,2026

Trainee Data Scientist

Deets Digital

My role involves extracting necessary data fields from PDF documents and converting them into structured JSON outputs.

  • Implemented Optical Character Recognition (OCR) using Tesseract OCR, PaddleOCR for text extraction.
  • Used OpenCV (cv2) for image preprocessing — improving OCR accuracy by handling issues like blur, low resolution and skewed text.
  • Extracted necessary data fields from PDFs and converted them into structured JSON outputs with accuracy and efficiency
  • Implemented Large language model(LLM) using Gemini 2.5 flash for data extraction.



Certification


Oct,2024-Jul,2025

Data Science

Fly The nest - Deets Digital

Wanted to uprage my skill for the data science so i joined the certified Data Science cource.

  • Learned MS Excel, MySQL, Python, PowerBI, Basic Statistics, Basic Machine Learning.
  • Also worked on the multiple projects involving Business insights and dashboarding during this Certification

Jan,2024-April,2024

Python - Django

CreArt Solutions

During the Acedemics I worked on two interships with the CreArt solution in the python django.

  • Built HelpingHand and Noticehub web apps using Django.
  • Designed models, views, and authentication workflows. Integrated CRUD operations and template rendering.
  • Used MySQL for efficient data storage and user management.



Research Paper


May,2025-Present

Data Analysis

Latest technology cources in India Technologies: Python, MS Excel.

During the Data science cource in the Fly the Nest we made a team of 4 members and started working in this research work with the help of or professor as a guide

  • Co-authoring an IEEE research paper on the Impact of Latest Technologies on education.
  • Conducting secondary data collection and using Python for cleaning and preparing educational datasets.
  • Applying data engineering to analyse technology trends in education and contributing to literature review and insight generation.



Education


2020-2024

Bachelor of Engineering

Computer Engineering

D.A. Degree Engineering and Technology(GTU)

CGPA: 7.82

2018-2020

Higher Secondary School

Hebron Higher Secondary School

Projects

Projects

Below are the projects on Ms Excel Dashboard, Django, Data Analysis(Python, MySQL), Python - OCR.

Blinkit Grocery Data Analysis Dashboard using MS Excel

Created a sales dashboard for Blinkit using Excel pivot tables and KPIs. Cleaned and analysed grocery sales data.

Pizza Sales Analysis

Analysed pizza sales to find top-performing items and seasonal trends using MySQL. Delivered insights using charts and a detailed report.

Udemy Course Data Analysis

Explored Udemy course data to identify revenue trends, pricing strategies, and course performance. Suggested actions to improve course engagement.


Zara Sales Data Analysis

Performed EDA on Zara's sales data using Python (Pandas, Seaborn).Uncovered trends in pricing, sales volume, and promotions.Suggested improvements in inventory and marketing strategy.

Salary Slip Automation & Expense Tracker

Developed a Python-based system using PaddleOCR to extract structured data from salary slip PDFs, automate updates to Google Sheets via API, and enable real-time salary and expense tracking with improved accuracy.

0 Research Paper
0 Internship
0 Projects
0 Tools & Technologies

Github

I love to solve business problems & uncover hidden data stories


GitHub

Contact

Contact Me

Below are the details to reach out to me!

Address

Ahmedabad, Gujarat, India

Contact Number

+ 91 9106735726

Email Address

pdhrumil079@gmail.com

Download Resume

resumelink



Find me on