Hi, I'm Ravi Varma,

About Me

I am keenly interested in creating and developing software that solves real-world problems using AI. Passionate about leveraging data to make efficient decisions by predicting the future. Although most of my work experience revolves around designing data-driven software, I am open and excited to explore other areas as well, as a Data Science Consultant or Machine learning architect and/or developer and/or engineer. Actively looking for full-time job starting from January 2020. I was previously a Data Science Consultant and Founder at Dynamic Cancer Care Pvt Ltd (Healthcare Startup) which was shutdown in September 2019, where I advised the team and led strategic data and technology initiatives for Cancer treatement and Oncologist. My experience in applied data science includes leading teams, helping build products, and independent research in the areas of healthcare, education, eCommerce, Banking and Finance.I started writing about seminal online machine learning, data science and deep learning resource. I am particularly interested in deep neural networks, natural language processing, algorithm design and optimization. I also post content for aspiring data scientists to help them enter the field and build a learning path to land their first role.

Skills

Python
SQL
R
HTML5
UNIX
LaTex
D3.js
Scikit-Learn
TensorFlow
Pandas
streamlit
PyTorch
Keras
NumPy
Django
Seaborn
Matplotlib
Jupyter
Tableau
Git
R Studio
PyCharm
Sublime Text
AWS
Google Colab
VS Code
MySQL
MS SQL Server
SAP BODS

Education & Experience

For more information, have a look at my curriculum vitae .

Projects

Built a chatbot using Rasa framework which interacts with users(Patient) and helps them to find a oncologist. User can book an appointment, User can check for the symptoms and Cancer related queries.

Python NLP Rasa Framework Django HTML

Auto classification of health care documents like prescription, doctor notes and health reports. Cancer Treatment Plan recommendations based on diagnosis. Researched new technology for our field, as well as new operational strategies, making recommendations for implementation. Collaborated with team to develop an internal tool that automates the creation of verified users. Create reports based on findings to be presented to executives at monthly board meeting, making recommendations for improvement in addition to raw information.

Python Scikit-Learn TensorFLow Matplotlib OpenCV

Open Source Projects

This portfolio is a compilation of notebooks which I created for data analysis or for exploration of machine learning algorithms. A separate category is for separate projects.

css html5 json yaml

Data Analysis, Visualization and Machine Learning Model Building in an interactive WebApp for Data Scientist/Data Engineer/Business Analyst. The purpose of this app is to create a quick Business Insights. AutoML WebApp built with Streamlit framework using Pandas and Numpy for Data Analysis, Matplotlib and Seaborn for Data Visualization, SciKit-Learn for Machine Learning Model.

automation heroku machine-learning matplotlib seaborn sklearn streamlit-webapp

Leveraging AI To Combat Pneumonia(COVID-19). Identifying medical diagnoses and treatable diseases like pneumonia from chest x-rays by Image-based deep learning using neural networks

ai cnn covid-19 deep-learning diagnosis pneumonia

Latex is a fantastic typesetting program that a lot of people use these days, especially the math and computer science people in academia.

cv latex markup resume

COVID-19(Coronavirus) CaseStudy, Analysis, Visualization and Prediction.

data-analysis data-visualization deep-learning fbprophet keras-models machine-learning-algorithms seaborn sklearn

Preprocessing Large Exploratory Data Analysis performed on Online Retail Data with 5,00,000(5 Lakh) observations. The purpose of this work was to see what value could be extracted from a fairly large dataset. The analysis includes some basic feature engineering and machine learning. I also used the opportunity to test LightGBM algorithm. I didn't have access to high performance computing resource and the algorithm served me well in terms of speed and accuracy, compared with XGBoost.

bigdata exploratory-data-analysis machine-learning naive-bayes-classifier sklearn

Contact

On the off chance that you might want to connect with me, be it for investigating innovation, business, startups or to simply say hello, don't hesitate to send me an email at ravivarmathotakura@gmail.com. If you see something incorrect, or that could be done better, or that just rubs you the wrong way, please let me know!