Bachelor degree of Mathematics.
Proficient in Python and R for data manipulation, visualization, and analysis. Well-versed in TensorFlow, pandas, NumPy, and Matplotlib for modeling an d visualization in the data world.
Personal Project
Personal Project
Ruangguru Engineering Academy Project
Personal Project
MySkill Academy Personal Project
Personal Project
Personal Project
Personal Project
Personal Project
Personal Project
Personal Project
Personal Project
In the fervent anticipation of the official announcement of the elected president by Indonesia’s General Elections Commission (KPU), social media, notably Twitter, has become a vital outlet for citizens to voice their opinions. This project introduces an automated system for sentiment classification. The goal is to develop Natural Language Processing (NLP) model to conduct Twitter Sentiment Analysis using TensorFlow library.
The House Sales Dashboard that I created using Tableau Public, focuses on daily prices, geographical trends, and key property features in the USA real estate market. It's a dynamic tool for professionals, investors, and homebuyers, offering valuable insights to navigate the dynamic world of USA real estate.
An user-friendly interface using Gradio for image classification pipeline that displays the image, and uses the Hugging Face's model to predict the age of the person in the image.
Hand counting detection that I developed with python and Open CV. This project enables real-time tracking and recognition of hand gestures, providing a firsthand experience of the code's simplicity. Uncover the potential for diverse applications, from interactive gaming to sign language interpretation, as we delve into the fascinating world of computer vision.
In this Python project, the objective is to calculate the percentage of customer retention. By employing data-driven methodologies, the project provides a straightforward analysis to measure and understand customer retention, a crucial metric for businesses aiming to build lasting relationships.
In my sales dashboard project developed with Google Spreadsheets, I aimed to streamline data analysis and visualization for a comprehensive overview of sales performance. Leveraging the collaborative features of Google Sheets, I organized and analyzed sales data efficiently. The dashboard provides a visual representation of key metrics such as revenue, product sales, and customer demographics.
XGBoost, short for eXtreme Gradient Boosting, is a machine learning algorithm known for its efficiency and effectiveness in handling complex datasets. It excels in regression problems, making it a perfect candidate for predicting continuous values like house prices. I developed this project with the aim of harnessing the predictive power of the XGBoost model to assist in the real estate domain.
My project, “Medical Diagnosis Chatbot Assistant” aims to use AI to make diagnoses related to a patient's disease. I use LLM version that has been developed by Meta, known as LLAMA-3.
This project focuses on classifying dog breeds using deep learning. The model is built using ResNet50, a pre-trained architecture fine-tuned on the Stanford Dogs dataset. The model achieved a training accuracy of 86.23% and a validation accuracy of 88.65%. This project can be used for applications such as pet identification, wildlife research, and mobile apps for breed recognition.
This project aims to detect fraudulent credit card transactions using machine learning algorithms such as Logistic Regression, Decision Tree, and Random Forest. I am applying preprocessing steps such as data cleaning, normalization, and handling missing values, along with feature engineering techniques, including transformation of transaction amount before training the models.
This project classifies movie genres using machine learning. It includes data preprocessing, feature extraction with TF-IDF or word embeddings, and model training with Logistic Regression, Decision Tree, and Random Forest. Evaluation is done using metrics like accuracy and F1-score, with visualizations for insights.
This project predicts customer churn in the banking sector using machine learning. After preprocessing the data, models such as Logistic Regression, Decision Tree, and XGBoost were trained. The XGBoost model achieved the highest accuracy at 85.05%, helping identify at-risk customers and develop retention strategies.
Marketing
Fulltime (July - Present)
Data Analytics
Internship (February - September)
Machine Learning
Bootcamp (July - October 2023)
Machine Learning cohorts
Studi independen (January - July 2023)
Data Scientist
Virtual Internship (August - October 2022)
All rights reserved © Aditya Gofi Saputra 2023.
