• Java as backend
• React JS as frontend
• Built in a microservice architecture with seperate services like
  • User service - handles authentication and store user info to User table
  • Task service - handles CRUD operations related to task
  • Submission service - handles CRUD operation related to submissions
• Login and Register functionality
• Admin panel
  • Create task
  • Edit task
  • Delete task
  • Assign task to user
  • View all submissions by user
  • Accept or Decline submissions
• User panel
  • View all task assigned by Admin
  • Create submissions for a particular task

• Express JS as backend
• React JS as frontend
• MongoDB atlas to store the data
• Login and Register functionality
• Create property listing with images
• Responsive design
• Book hotels and view your bookings
• View all the listed accomodations

• Express JS as backend
• React JS as frontend
• MongoDB atlas connectivity
• Login and Register functionlity
• Create, Edit and Delete post
• View other blog post

• Flask as backend
• Forms and validation
• SQL Database connectivity
• Login Authentication
• Creating and deleting blog posts

• HTML, CSS, Javascript

• HTML, CSS, Javascript

• HTML, CSS, Bootstrap5, Jquery

• HTML, CSS, Javascript

• HTML, CSS, Bootstrap5

• Mongo DB atlas DB connectivity
• Rest API
• Spring boot

Telco customer churn prediction

Predicting customers who will churn using logistic regression

• Doing exploratory data analysis for identifying important features
• Encoding categorical variables to use them in machine learning models using DictVectorizer
• Using logistic regression for classification and tuning the parameters to improve performance.
• Saving models with Pickle and serving models using Flask
• Managing dependencies with Pipenv and making the service self-contained using Docker

Credit risk scoring prediciton

Predicting the risk of defaults using different tree-based models

• Using decision trees to predict and implement a basic decision tree learning algorithm
• Using Random forest to predict and tuning the parametes to improve performance
• Using Gradient boosting to predict and tuning the parametes to improve performance
• Selecting the best model by evaluating the auc scores on validation dataset.

Car price prediction

Creating a car-price prediction project with a linear regression model

• Performing an initial exploratory data analysis with Jupyter notebooks.
• Setting up a validation framework
• Implementing the linear regression model from scratch
• Performing simple feature engineering for the model
• Keeping the model under control with regularization
• Using the model to predict car prices

• Downloading historical stock prices from Yahoo finance
• Performing exploratory data analysis
• Setting up data to predict future prices using historical prices
• Training the model using Random Forest
• Setting up a bactesting engine
• Improving the accuracy of the model

• Using request and BeatifulSoup library to scrap data from fbref.
• Performing exploratory data analysis
• Using Random Forest to generate prediction
• Performing feature engineering to improve the accuracy.

• Performing Exploratory data analysis
• Handling missing values and Data manipulation
• Feature engineering
• Using different models like linear regression, random forest and gradient boosting.
• Hyperparameter tuning using GridSearchCV
• Evaluating the model based on cross validation score and root mean squared error score.
• Choosing the best model.