Powered by
Codebasics DS Foundation Bootcamp

Susmit Anand Shingne

Data Aspirant

+91 7498713703 [email protected]

Resume

Hello, I am

Susmit Anand Shingne.

2

Python Projects

2

Machine Learning Projects

About Me

Aspiring Data Scientist | Machine Learning Enthusiast | Engineering Student
I am an engineering student passionate about data science, machine learning, and full-stack web development. With hands-on experience in SQL, Python, FastAPI, React, and Flask, I have worked on projects ranging from credit risk modeling and healthcare premium prediction to secure web applications.
Beyond technical skills, I am highly analytical, detail-oriented, and driven by problem-solving. I am currently preparing for a master’s degree in Germany, aiming to deepen my expertise in AI, data-driven decision-making, and fintech applications.

Let’s connect and collaborate on innovative tech solutions!

Key Skills

Python

SQL

Maths and Statistics

Machine Learning

Jupyter

REST APIs

EDA

Python Libraries

Git

Streamlit UI

Visualisation

Predictive Modelling

My Projects

Awards & Certificate

Python: Beginner to Advanced For Data Professionals

SQL for Data Science

Math and Statistics For AI, Data Science

Master Machine Learning for Data Science & AI: Beginner to Advanced

Let's Connect

Feel free to get in touch with me. I am always open to discussing new projects, creative ideas or opportunities to be part of your visions.

[email protected]

https://www.linkedin.com/in/susmit-shingne-771a40304/

+ 91 7498713703

https://github.com/SUSMIT-6704

Python Project

Exploratory Data Analysis in Hospitality Domain

Domain/Function: Hospitality Domain

This project analyzes booking trends, customer segmentation, revenue patterns, and cancellations in the hospitality industry using Python, Pandas, and Seaborn. Insights help optimize pricing, improve customer experience, and enhance operational efficiency.

View Project
Engagement

View Project
on GitHUB

Exploratory Data Analysis in Hospitality Domain

City Value Counts

Exploratory Data Analysis in Hospitality Domain

pie chart of revenue realized per booking platform

Project Details

Exploratory Data Analysis (EDA) in the hospitality domain involves analyzing data from hotels, restaurants, and services to uncover insights and trends. It includes data collection from sources like bookings, customer reviews, and sales data, followed by cleaning to handle missing values and outliers. Visualization tools like histograms and heatmaps help reveal patterns in customer behavior and booking trends. Descriptive statistics summarize key metrics, such as average ratings and occupancy rates. Correlation analysis explores relationships between factors like price and customer satisfaction, while segmentation groups customers based on booking habits and preferences. EDA helps businesses optimize operations, enhance customer experience, and predict future trends.

Python Project

Expense Tracking System

Domain/Function: Expense Tracking

The "Expense Tracking System" is a web application that helps users track and manage their expenses. Built with Streamlit for the frontend and FastAPI for the backend, it offers a simple, interactive interface to log, categorize, and analyze spending patterns. Ideal for efficient expense management

View Project
Engagement

View Project
on GitHUB

Expense Tracking System

main home page

Expense Tracking System

expense breakdown by category

Project Details

The "Expense Tracking System" is a full-stack web application designed to assist users in managing their finances by tracking and categorizing their expenses. The frontend is developed using Streamlit for a responsive and intuitive interface, while the backend utilizes FastAPI for handling API requests. This system allows users to input, view, and analyze their spending habits with ease. It also includes a database for storing data and ensures seamless interaction between the frontend and backend. The project showcases skills in web development, API integration, and database management.

AtliQo Credit Card Launch

Domain/Function: Maths And Statistics

The AtliQo Bank Credit Card Launch Project includes two phases: Phase 1 identifies the target market for a new credit card, focusing on customer segmentation. Phase 2 uses A/B testing to refine strategies for optimizing credit card adoption, ensuring effective market engagement.

View Project
Engagement

View Project
on GitHUB

AtliQo Credit Card Launch

Overall Analysis

AtliQo Credit Card Launch

Product category And Platform Count

Project Details

The AtliQo Bank Credit Card Launch Project is divided into two phases. Phase 1 focuses on identifying the target market by analyzing customer demographics, behaviors, and preferences. Phase 2 involves A/B testing to refine and optimize credit card adoption strategies, enhancing user engagement and conversion rates. The project combines market research with data-driven testing to create a robust launch strategy for maximizing the success of the credit card.

Machine Learning Project

Healthcare Premium Prediction

Domain/Function: Regression

This project uses machine learning (regression) to predict healthcare insurance premiums. It analyzes factors like age, BMI, and smoking status to estimate costs.

View Project
Engagement

View Project
on GitHUB

Healthcare Premium Prediction

Main Home Page

Healthcare Premium Prediction

Main Home Page

Project Details

This project, "Healthcare-Premium-Prediction," focuses on developing machine learning models to predict healthcare insurance premiums. It utilizes regression algorithms, trained on datasets containing patient demographics and lifestyle factors (age, BMI, smoking status, etc.), to estimate insurance costs. The goal is to provide accurate premium predictions, enabling users to better understand and manage their healthcare expenses. The project demonstrates a practical application of machine learning in the healthcare finance domain, potentially aiding in cost transparency and planning.

Machine Learning Project

Credit Risk Modelling

Domain/Function: Classification

Developed a Machine Learning model to classify credit risk, enhancing loan default prediction for financial institutions. Implemented data preprocessing, feature engineering, model training, and evaluation to improve decision-making and risk assessment.

View Project
Engagement

View Project
on GitHUB

Credit Risk Modelling

Home User Interface

Credit Risk Modelling

Streamlit Interface

Project Details

Designed and implemented a Machine Learning model to assess credit risk, aiding financial institutions in predicting loan defaults. The project involves data preprocessing, feature engineering, model selection, training, and evaluation. Various classification techniques were explored to enhance predictive accuracy. This model helps in making informed lending decisions by identifying high-risk applicants, optimizing loan approvals, and minimizing financial losses. The repository includes a well-structured workflow with exploratory data analysis (EDA), feature importance analysis, and performance metrics to ensure model reliability.