Originally from Ranchi, Jharkhand, India, I have experience working as a Data Analyst using Python and other BI tools on SQL Databases. I have around 2.8 years of experience working directly with clients in full-time role and engaging directly with clients as a Freelancer. My work encompassed different technologies as a part of my development, designing and testing, incorporating Python technologies and different libaries to perform Analytical and Visualisation tasks incorporating Pandas, NumPy, Flask, RESTful Web Services to name a few. I also have a good amount of experience in BI tools namely, Power BI, Tableau and Google Analystics.
Besides this I also am an avid Football Fan,(aka Soccer to a few) and true to Liverpool FC. My hobbies include watching Netflix and street photography. I also have keen interest in playing Sudoku while my models are taking forever to train.
With expeience in management of team members and handling clients through an Agile way of working, this is one of the most important facets of my work.
Worked with large sets of data to extract insights, including collecting and organizing data, using statistical analysis to identify patterns, creating visualizations, and building models for predictions. Communicated findings to stakeholders and made recommendations based on the results.
Strong grasp in the Regression and Clustering predictive models used in Python to build Predictive models with high accuracy with data sourced and cleaned from different sources be it structured or non structured or a REST API.
Well versed in Oracle® Data Warehousing using PL/SQL and highly challenging scenarios involving NoSQL databases like MongoDB®.
Click to view the dashboards and prediction models on my GitHub...
Built logistic regression and decision tree models to predict earthquake damage to buildings, extracted data from a #sqlite database, and revealed the biases in the data that can lead to discrimination. Details
Built a dashboard to showcase the team wise performance over the years of all the Premier league teams highlighting their stats like Goals, Corners, fouls, matches played etc Details
Understanding the sentiment around the Pfizer vaccine will be helpful in understanding how the public feels, and indicate how receptive they are to taking the vaccine.
With the SentimentIntensityAnalyzer imported from VADER, we can not only gather count of sentiment for the tweets, but classify them and create a new column that labels the tweet Positive, Negative, or Neutral. This labeling can be used to show difference between sentiment. I will also show how sentiment has looked over time.Details
Understanding the popularity of tracks on Spotify which will be helpful in understanding how the public feels, and indicate what actually is the mass listening.
With the XGBoost and other Regression models gather sentiment for the songs, artists and albums.Details
Understanding the factors affecting the price of a Car which will be helpful in understanding how the Auto industry market functions, and indicate what Selling Price of a car would be from the data available.
With the Random Forest Regressor and other Regression models gather insights for the auto industry from the Kaggle's CarDekho.com dataset.Details
Built an #arma time-series model to predict particulate matter levels in Kenya, extracted data from a Mongodb database using PyMongo, and improved model performance through hyperparameter tuning.Details
Created a GARCH time series model to predict asset volatility, acquired stock data through an API, cleaned and stored it in a SQLite database, and then built an API to serve model predictionsDetails
Built a k-means model to cluster US consumers into groups, used principal component analysis (PCA) for data visualization, and then created an interactive dashboard with Plotly Dash Details
Built a tool that suggests movies to users based on their past preferences and ratings. This project used machine learning libraries in Python, including Bag of Words and Streamlit, to build a recommendation system. The TMDB dataset was used to train and test the model. The system first preprocessed the data, extracting relevant features and cleaning the dataset. Then, it used the Bag of Words method to convert the movie plot summaries into numerical feature vectors, which were used to train the recommendation model. The model was then deployed using the Streamlit library, allowing users to easily interact with the system and receive personalized movie recommendations. Details
Let me walk you through my journey of schooling in India where I was born and brought up along with my university life. I also elaborated on my work experience.
February 2023 - Present
August 2022 - December 2022
• Analyzed and interpreted large data sets to identify trends and patterns for research project.
• Developed and implemented data analytics models to improve decision-making for the stakeholders.
• Utilized tools such as Python, and SQL to build and deploy machine learning models to measure and track KPIs such as
accuracy, precision, and recall
• Communicated findings and insights to stakeholders through reports, presentations, and visualizations.
June 2021 - March 2022
• Streamlined the billing process for a British telecom company working in an Agile Scrum team increasing manual
reporting efficiency by 30%.
• Built out the data and reporting infrastructure from the ground up using Power BI and SQL to improve customer
communication processes by 18%.
• Devised complex SQL queries in collaboration with cross-functional teams to provide actionable insights for
businesses.
• Developed precise specifications for project plans through customer requirements to improve productivity by
75%.
• Built ETL solutions to consume multiple data sources and implement necessary business logic to feed the data
into reporting data.
• Directly interacted with clients, understood requirements, and proposed suitable solutions, ensuring quality
and timely implementation.
• Compiled, studied, and inferred large amounts of data, modeling information to drive auto policy pricing.
July 2021 - November 2021
• Collaborated on stages of SDLC from requirement gathering to production for a leading Dutch bank as a Python developer in an Agile Scrum team to improve QoQ VAT audit by 130%.
• Overhauled obsolete legacy source code in Python and SQL to reduce the average load on DB servers in peak season by 25%.
• Identified procedural areas of improvement through customer data, using SQL to tweak the SBV auditing.
• Compiled data and generated graphs using Python libraries to interpret results and suggest key operational improvements to stakeholders through dashboards which saved over 100k Euros in cloud server costs.
• Facilitated Scrum framework – sprint planning, backlog grooming, daily scrums, sprint reviews, and sprint retrospectives with the business stakeholders.
June 2011 - June 2015
Pursued graduation in Computer Science and Engineering. Distinction grades in Data Visualisation, ML Fundamentals, Python Programming, Operating Systems, System Architecture and Cloud Computing. Was part of Organising committee of TEDX SRMIST and led as GC of Design and Art for Roobaroo, college fest
May 2015
Completed AISSCE board exams
Use this space below to convey your message.