Theofilus Arifin's repositories
Airline-Customer-Segmentation
Conducted univariate and multivariate analyses on a dataset of 62,989 rows and 23 columns. Segmented using the RFM method and K-means clustering, revealing two groups via elbow method determination.
Aksara-Document-Transliteration-Using-Object-Detection-and-Automata
Explore Aksara Jawa effortlessly with YOLOv8 and Finite State Automata-powered Transliteration that i developed. Achieving high metrics (Train: 0.967/0.922/0.961, Validation: 0.966/0.924/0.961), our Streamlit interface ensures easy input and accurate output. Unlock precision and simplicity in Aksara Jawa to Latin conversion.
Analyzing-eCommerce-Business-Performance-with-SQL
In any company, measuring business performance is crucial for tracking, monitoring, and evaluating the success or failure of various business processes. Therefore, this project aims to analyze the business performance of an eCommerce company, considering several business metrics: customer growth, product quality, and payment types.
Investigate-Hotel-Business-Using-Data-Visualization
Investigating business performance is crucial for any company. In this project, we delve into the hospitality industry, aiming to understand customer behavior in hotel bookings and its correlation with cancellation rates. We present our insights through data visualization for better comprehension and persuasive presentation.
Predict-Customer-Personality-To-Boost-Marketing-Campaign-By-Using-Machine-Learning
In today's competitive business landscape, understanding customer behavior is paramount for marketing success. By gaining insights into customers' unique personality traits and preferences, companies can tailor their strategies to boost engagement and conversion rates.
Text-Classification-for-Craigslist-Posts
This project aims to classify Craigslist posts into different categories based on their heading. It utilizes machine learning models to predict the category of a given heading within a selected city and section.
AnythingLLM-Study
AnythingLLM is the easiest to use, all-in-one AI application that can do RAG, AI Agents, and much more with no code or infrastructure headaches.
Diabetes-Disease-Prediction
Diabetes, characterized by high blood sugar levels due to ineffective insulin production or usage, poses serious health risks if not managed. Deep Learning offers promising avenues for diabetes management.
Dify-Study
Dify is an open-source LLM app development platform. Orchestrate LLM apps from agents to complex AI workflows, with an RAG engine. More production-ready than LangChain.
DVC-Study
Even with all the success we've seen in machine learning, especially with deep learning and its applications in business, data scientists still lack best practices for organizing their projects and collaborating effectively.
E-Commerce-Data-Analysis-with-Elastic-Search
This project involves comprehensive e-commerce data analysis using SQLite and Elasticsearch. It starts by importing the Kaggle E-commerce dataset into SQLite for initial exploration and basic data cleaning. Then, Elasticsearch is employed for indexing and querying, enabling further analysis.
EmoTweetAI-Classifying-Emotions-in-Tweets
EmoTweetAI is a sentiment analysis system designed to classify emotions in Twitter uploads. It categorizes tweets into positive, negative, or neutral sentiments, providing valuable insights into public opinion on various matters.
Exclusive-Product-Classification
In today's competitive market, understanding what makes a product exclusive can provide valuable insights for businesses. This project aims to develop a classification model to categorize products as exclusive or non-exclusive based on various attributes.
FIFA21-Valuable-Player-Prediction
This project aims to predict valuable players in FIFA21 using machine learning techniques. In the world of professional soccer, identifying valuable players is crucial for clubs in building successful teams and making strategic decisions in player recruitment and management.
House-Pricing-Prediction
Real Estate refers to tangible properties such as land, buildings, or other structures, which can serve as investment assets or a source of income through rent or property sales. Machine Learning plays a crucial role in the real estate industry by predicting property prices based on factors such as location, size, amenities, and property condition.
OCR-Based-Weight-Measurement-System
This project is an OCR (Optical Character Recognition) based weight measurement system that utilizes the Easy OCR library and color segmentation techniques. The system is designed to extract weight information from images of weighing scales and display the result.
Predicting-German-Credit-Risk-with-PyTorch
This project focuses on predicting credit risk using deep learning techniques implemented with PyTorch. We leverage the German Credit Risk Dataset, which contains various attributes representing the credit profiles of individuals. Our goal is to build a robust predictive model that can assess the creditworthiness of applicants.
Predictive-Modeling-for-Term-Deposit-Subscription-in-Bank-Marketing
The project aims to optimize the fixed deposit marketing campaign by efficiently targeting potential subscribers, thereby maximizing resource allocation and effectiveness.
prompt-engineering
Prompt engineering is a crucial aspect of working with advanced AI models like GPT-4. It involves designing and structuring inputs (prompts) to guide the model to produce desired outputs. Understanding different techniques and approaches in prompt engineering can significantly enhance the performance and accuracy of AI models.
Sentiment-Analysis-on-2019-Indonesia-Election
This project aims to analyze the sentiment of tweets related to the 2019 Indonesia Election. Sentiment analysis plays a crucial role in understanding public opinion and attitudes towards political events, providing valuable insights for decision-making and public discourse.
Text-Summarization
Text Summarization automates the creation of concise and understandable summaries from original text, assisting executives in efficiently comprehending complex documents. Leveraging computational methods, the project identifies key points and contextual cues to generate informative summaries, enhancing productivity and comprehension.
Theofilusarifin
This is my ReadMe code on my Github profile.
Time-Series-Forecasting-of-Vehicle-Speed-on-Roadway
This project explores data analysis and time series forecasting to understand average vehicle speed on a roadway, crucial for traffic management and congestion reduction.
Youtube-Views-Pediction
The YouTube View Prediction Project aims to develop a machine learning model capable of forecasting the potential number of views a video might receive on the YouTube platform, by leveraging various factors such as title, likes, comments, description, and other relevant elements.