Samuel Samraj's repositories
Employee-Attrition-Analysis-and-Prediction
This project aims to provide insights into the factors influencing employee attrition and predict which employees are likely to leave the company.
My-Train_Chatbot
MyTrain Chatbot simplifies accessing Indian train schedules via text/voice input with multi-language support. It retrieves train options, offers seat preferences, rectifies errors, and recommends alternatives, enhancing travel planning and user experience.
Web-Scraping-with-BeautifulSoup
Developed a Python script using BeautifulSoup to scrape data from an attached file, extracting relevant information such as text. Stored the scraped data in a structured format (CSV), meeting the task requirements for submission via email and Google Form.
SPEECH---TO---TEXT-CONVERT
"Speech to Text GUI is a Python application that provides a user-friendly interface for transcribing audio files into text, supporting multiple languages such as English, Tamil, and Hindi."
Sports-Analytics
This cricket player performance analysis project evaluates player fitness and form for an upcoming T20 game. By analyzing career statistics and performance metrics, it assists team management in informed decision-making for player selection and game strategies.
Financial-Risk-Detection
This project combines EDA and machine learning to predict loan defaults for a consumer finance company. Analyzing historical loan data reveals patterns indicating potential defaulters. By minimizing financial losses and avoiding unfair rejections, this analysis aids in efficient risk management.
Predict_Rental-_Property_Prices
This project employs machine learning to predict residential property rents, utilizing features like location, amenities, and property details. Through model evaluation and feature importance analysis, it aims to enhance pricing strategies for landlords and rental decision-making for tenants.
Energy-Consumption-Analysis
. We aim to identify trends, assess conservation effectiveness, and pinpoint areas for improvement, informing data-driven strategies to achieve climate change mitigation goals within the BPS.
Page-Optimization-User-Engagement-Strategy-Analysis
"Python-based analysis of user behavior and marketing campaigns to optimize business growth. Actionable insights and strategic recommendations for enhanced user engagement and sales performance."
Car-price-prediction
The primary objective of is project is to create a data science solution for predicting used car prices accurately by analyzing a diverse dataset including car model, no. of owners, age, mileage, fuel type, kilometers driven, features and location. The aim is to build a ML model that offers users to find current valuations for used cars
multiplex-SWOT-analysis
"Multiplex exhibits strengths in providing diverse entertainment options and a superior viewing experience. However, challenges in fluctuating film industry trends and potential competition highlight the need for strategic adaptation, making a comprehensive SWOT analysis crucial for sustained success."
Fast-food-swot-analysis
"Hunger offers a compelling investment opportunity in the food industry with a focus on quality ingredients, a unique menu, and standard discounts, presenting a franchise with rapid returns and a strong market presence."
Recommendation_System
Udemy Course Recommender: A Python project implementing Popularity-Based and Content-Based recommendation systems for Udemy courses, featuring a Tkinter-based GUI for interactive user experience.
News_Classifier
NewsClassifier is an NLP-based project that classifies news articles into topics using web scraping, text preprocessing, clustering, and machine learning. The system incorporates a Streamlit application for user-friendly deployment.
Mall_Customer_Segmentation
This project utilizes KMeans clustering to perform customer segmentation based on annual income and spending score. It includes a Jupyter notebook for model training and a Tkinter GUI for predicting customer segments interactively.
IMDB_Analysis
Explore the dynamics of movie success on IMDB through a comprehensive analysis. Uncover insights into the influence of genres, duration, language, directors, and budgets on IMDB ratings. The project offers actionable findings for stakeholders in the film industry, presented with compelling visualizations in Power BI dashboards.
Insurance-Cost-Prediction
The provided Python script utilizes scikit-learn for training machine learning models to predict insurance charges based on features such as age, BMI, and smoking status. Additionally, it incorporates Tkinter to create a simple GUI for user input and model prediction display.
Loan_Approval_Prediction
Predicting loan approval using data analysis and machine learning. Explored factors like CIBIL score, assets, and more. Implemented Decision Tree and Random Forest models, achieving 98.3% ROC AUC. Find insights in the Jupyter Notebook. #DataScience #MachineLearning #Finance
movies_metadata_cleaning
Cleaned and standardized the Movies Metadata dataset to address issues such as missing data and mismatched data types, ensuring data quality and consistency.
Airbnb-Analysis
The Airbnb Analysis Project seeks to optimize property listings and enhance user experiences by analyzing data on trends, preferences, and pricing dynamics. With a focus on data science, the project aims to provide valuable insights for hosts and improve booking satisfaction for guests.
Industrial_Copper_Modeling
ndustrial Copper Modeling project. Python, ML regression/classification, EDA, Streamlit app for accurate pricing and lead classification in the copper industry. Skills: Python, Data Preprocessing, EDA, ML, Streamlit. Domain: Manufacturing
Product-Review-Analysis---FlipKart-Amazon
Utilizing ML and NLP, this project analyzes customer reviews on e-commerce platforms, categorizes sentiments, computes ratings, and generates ranking tables for mobile phones. It aims to enhance FMCG product quality and customer satisfaction.
Flight_Price_prediction
This repository provides an end-to-end solution for predicting flight ticket prices. It includes data collection, exploratory data analysis (EDA), data preprocessing, and model selection. The chosen model, XGBoost, achieves an RMSE score of 12.5, demonstrating accurate price predictions.
E-Commerce-Analytics-Project
This project focuses on analyzing an e-commerce dataset to derive valuable insights that can aid in making informed business decisions. The dataset encompasses various aspects of e-commerce transactions, including customer behavior, product details, and sales information.
Project-Title-YouTube-Data-Harvesting-and-Warehousing-using-SQL-MongoDB-and-Streamlit
Skills take away From This Project Python scripting, Data Collection, MongoDB, Streamlit, API integration, Data Managment using MongoDB (Atlas) and SQL
BizCardX-Extracting-Business-Card-Data-with-OCR
BizCardX: A Business Card Data Extraction Tool with OCR BizCardX is a Python-based tool that simplifies the process of extracting and managing information from business cards using Optical Character Recognition (OCR). With the EasyOCR library, it effortlessly extracts text from images, while the Streamlit-based graphical user interface provides a
phonepe_pulse
Domain : Fintech | Data visualization and exploration with Plotly library and built interactive dashboard using Streamlit
SCIENTIFIC-CALCULATOR
skills take away from this project PYTHON scripting, and GUI (tkinter)