I'm Dhruvil Jhala


Diving into a world where numbers not only talk but crack jokes too, I'm a passionate engineer with a Master's degree in Data Science from Northeastern University and a solid background in Computer Science. I leverage my expertise in Machine Learning, Natural Language Processing (LLMs), Data Analysis, and Data Engineering to solve complex problems and drive business impact.

I am a continuous learner and enjoy staying updated on the latest advancements in the field of data science. I am proficient in a variety of programming languages and tools, including Python, R, SQL, Java, Spark, TensorFlow, PyTorch, Databricks, and Tableau.

  • Timeline

  • Software Development Engineer Intern

    Amazon LLC (June, 2023 - Sept 2023)

    Designed and implemented a Vendor Support Portal to offer real-time data insights & boost efficiency for Vendor Managers. Led a full-stack project, involving the creation and modification of existing APIs, and A/B testing to assess efficacy. Extracted and processed data from AWS DynamoDB and updated frontend UI resulting in improved data accessibility. Integration of the dashboard with relevant data resulted in a 15% decrease in support tickets generated for the business team, and enhanced analytics capabilities for vendor managers.

  • Data Scientist Co-op

    Peapod Digital Labs (Jan 2023 - June 2023)

    Designed a robust Embedding Evaluation Toolkit on Databricks to assess word embeddings from various LLMs, achieving a 7% increase in customer purchase rates. By fine-tuning the T5 XL model and optimizing data selection, I reduced processing time by 66%. Additionally, I enhanced precision and recall for Search & Substitution cases by developing a Named Entity Recognition solution, resulting in a 9.5% overall improvement.

  • Research & Teaching Assistant

    Northeastern University (May, 2022 - Current)

    Supported and mentored student development in advanced Python programming through weekly office hours and lab sessions. Evaluated and assessed the assignments of over 400+ students in alignment with the curriculum. Studied neural processes in perception, predicting hand movements in the Trail Maker Test using three input devices.

  • Master of Science in Data Science

    Northeastern University (Jan, 2022 - Current)

    I began my adventure as a Master of Science student in Data Science at Northeastern University. I've been studying courses like Data Mining, Database Management, Algorithms, Natural Language Processing, and Large Language Models as part of my program.

  • Data Analyst

    Ernst & Young, Mumbai (July, 2021 - Nov 2021)

    Collaborated with clients across 11 international offices, analyzing extensive financial data within client software. Utilized Tableau for data visualization and optimized SQL queries for analysis, making complex financial data understandable for stakeholders and enhancing decision-making process. Performed assessments, tested the operating effectiveness of the IT automated controls, and identified the deficiencies.

  • Data Science Intern

    iSimle Technologies, Illinois Chicago (June 2020 - September 2020)

    Developed a Deep Learning model for a new Neuromarketing method with 77% accuracy. Also, I handled big sets of messy data, visualized patterns and trends with tools like Matplotlib and Seaborn. I set up the model on Google Cloud, optimized data flow with Kubeflow, and fine-tuned parameters for better performance.

  • Machine Learning Intern

    Smart Bridge, Hyderabad, India (May 2020 - June 2020)

    I worked on a project to predict Life Expectancy of people all over the world based on 14 factors. The Machine Learning, regression model was created on IBM Watson Studio and deployed on IBM Node Red service with an accuracy of 89 percent.

  • Treasurer & Machine Learning Workshop Tutor

    Computer Society of India (CSI) - (May 2020 - June 2021)

    During the tenure, I functioned as Treasurer and further I volunteering to work as tutor for Machine Learning workshop sereis to the freshmen and second year students in my college.

  • Academic Support Volunteer

    Make A Difference (MAD) - (May 2020 - May 2021)

    I worked as an Academic Support Volunteer with an Indian non-profit organization namely Make A Difference (MAD), where I volunteered to teach math course to unprivileged students.

  • Bachelor of Technology in Computer Engineering

    Narsee Monjee Institute of Management Studies (June 2017 - May 2021)

    I was admitted to the Bachelor in Computer Science program at Narsee Monjee University of Management Studies (NMIMS). This curriculum equipped me with a strong foundation in essential technical principles.

  • Secondary & Higher Secondary Education

    St. Xavier’s High School, Gandhinagar (2015 - 2017)

Projects



Northeastern’s OGS RAG ChatBot

Built an AI chatbot for Northeastern’s Office of Global Services leveraging LangChain’s document processing pipeline. Employed ChromaDB to construct a searchable database of text embeddings, enabling fast similarity search on questions. Leveraged LLMs like GPT-2 and DistilBERT for initial response generation and Gemini-Pro for enriched responses.

Predicting IVF Success Rates

The research project is based on predicting final outcome of IVF procedure, based on Day 3 EmbryoAnalysis and Patient Characteristics. The mobile application will show results based on the 3 modelsdeployed over GCP. This project will boost the accuracy of IVF procedure from 20% to 85% or more.  

Neuro-Marketing

Project aims on getting electrophysiological data from human brain using EEG technique to analyse a new product before launching it in market. Currently using Random Forest, SVM, Neural Network algorithm to make it the worlds most accurate algorithm in the field

Predicting Life Expectancy using Machine Learning.

This is a Regression based Machine Learning project which leverages historical data with 14 features to predict insights into the future. This problem statement is aimed at predicting Life Expectancy rate based on various factors with an accuracy of 89 percent. The Machine Learning model is linked to Node-Red user interface. Project link - https://tinyurl.com/ya9klkuz

Sentiment Analysis of COVID-19 Tweets Dashboard

This was a IBM Hack Challange 2020 topic to perform sentiment analysis of Indians after the extension of lockdown announcements to be analyzed with the relevant tags on twitter and build a predictive analytics model to understand the behavior of people if the lockdown is further extended. The project uses Tweepy API to fetch tweets on runtime and created the visualization dashboard on IBM Watson platform itself.

IMDB based Movie Recommendation System

The project use Supervised algorithms like Naive Bayes. This is a Similarity based movie recommendation system based on imdb dataset. Collaborative Filtering and Jaccard similarity are used for predictions and MSE is used to get the precision of algorithm.

Attendance Manager Android Application

Attendance Manager is an android application to manage attendance of any student eciently. It is developed using API level 21 and v7 library package.

Multi-Purpose Student Query Portal

Tkinter library which is standard python GUI toolkit is used to link the interface with SQL database and performs search, fetch, input like operations .

Publications


Dhruvilsinh Jhala, "Predicting Embryo Viability to Improve the Success Rate of Implantation in IVF Procedure: An AI based Prospective Cohort Study" - Advances in Intelligent Systems and Computing Series (2020), Springer.

Dhruvilsinh Jhala "Review on Smart Supply Chain Management using IoT and Machine Learning", International Journal of Innovative Research in Science, Engineering and Technology (September 2019)

Dhruvilsinh Jhala, Predicting Chances of Live Birth in IVF procedure based on Day 3 Embryo Analysis and Patient Characteristics



Tech Stack 🛠


Python  Ruby  C++  MSExcel  HTML5

GCP  Firebase  MySQL 

Tenserflow  Pandas  Keras  Numpy 

Windows  iOS  Ubuntu 



Certifications


Deep Learning Specialization - deeplearning.ai (Ongoing)

IBM Data Science Professional Certificate (9 Courses) - IBM

Machine Learning A-Z: Hands-On Python R In Data Science - Udemy

Custom Prediction Routine on Google AI Platform - Rhyme

Deploying Machine Learning Models - UC San Diego

Merit Certificate for technical training in Python, Data Structure using Python, Database management system and Algorithms - Face Prep

Get in touch

Feel free to contact me.