Andrew Tanubrata's Projects
Artificial Intelligence using Reinforcement Learning Techniques to learn how to play the snake game
Associated with British Airways - Providing a Exploratory Data Analysis through web-scraping reviews from websites
This particular piece of text pertains to the coding structure that serves as the foundation for the online platform that I have developed for personal use. The intricacies of this source code are essential in ensuring the functionality and aesthetic appeal of the website that reflects my personal brand and identity.
Don't mind this, This is a special repository for my GitHub Profile
Applying Computer Vision techniques for the purpose of identifying and recognizing the presence of unoccupied parking spaces within a given area is a sophisticated and innovative approach. By utilizing advanced algorithms and image processing methods, this technology enables the automated detection of available parking spots.
Detecting Aberrations in Financial Transactions through the utilization of Deep Autoencoder Networks involves the application of sophisticated machine learning techniques that are specifically designed to identify irregularities or anomalies within large sets of financial data.
Datasets & Analyses for Formula 1 World Championship
This repo is just my study notes, whoever wishes to learn are welcome to take some of my notes
"Picasso" is a machine learning image classification model. At its core, the CNN architecture is intricately designed, achieving a remarkable pattern recognition capability. The training and evaluation rigorously validate the model, evidenced by an outstanding accuracy of 99.22%.
A sophisticated and cutting-edge online platform has been developed in the form of a web-based application designed specifically for the purpose of monitoring and tracing the International Space Station (ISS) in real-time as it orbits the Earth through a three-dimensional representation of the planet.
Stock Price Prediction using Recurrent Neural Network (RNN)
Utilized Python for Monte Carlo simulation to enhance supply chain efficiency amid demand fluctuations in five markets. Developed a decision model for factory location selection, comparing low and high-capacity facilities. Conducted 50 simulation scenarios and used a solver to determine the optimal supply chain network based on frequent solutions.