This project focuses on creating a Customer Churn Prediction Model using Decision Trees. By analyzing customer data, including usage patterns and interactions, the model identifies potential churn risks. Leveraging the interpretability of Decision Trees,

EBONICA SALETH

Data Scientist

About Me.

🚀 Computer Science student with a passion for solving real-world problems. Proficient in Python, SQL, and ML frameworks. Expertise in LIME and SHAP for Explainable AI. Actively seeking Data Science and AI internships to contribute to impactful projects and make a mark in the field. 🌟

PROFILE :

https://www.linkedin.com/in/ebonica-saleth-92b268224

GITHUB LINK:

https://github.com/Ebonica

PROJECTS :

SENTIMENT ANALYSIS USING NATURAL LANGUAGE PROCESSING FOR MOVIES REVIEW DATASET(POSITIVE OR NEGATIVE)

This project employs Natural Language Processing (NLP) to swiftly classify movie reviews, enhancing the efficiency of assessing audience reactions. The initial phase involves collecting and cleaning a diverse dataset of movie reviews, followed by an exploratory data analysis to gain insights into sentiment distribution. Text tokenization, utilizing techniques like TF-IDF or embeddings, is coupled with experimentation on various models, including Support Vector Machines and Random Forest.

GITHUB LINK: https://github.com/Ebonica/CODE-CRAFTERS-DATA-SCIENCE-EBONICA-SALETH

LINKEDIN LINK: https://www.linkedin.com/posts/ebonica-saleth-92b268224_datascience-careergrowth-codecrafters-activity-7135938507881029634-l1gz

2. CUSTOMER CHURN PREDICTION WITH DECISION TREES

This project focuses on creating a Customer Churn Prediction Model using Decision Trees. By analyzing customer data, including usage patterns and interactions, the model identifies potential churn risks. Leveraging the interpretability of Decision Trees, the project aims to provide actionable insights for businesses to implement targeted retention strategies. Using Python and scikit-learn, the model offers a concise solution for anticipating and addressing customer churn, ultimately enhancing customer satisfaction and loyalty.

GITHUB LINK: https://github.com/Ebonica/CODE-CRAFTERS-DATA-SCIENCE-EBONICA-SALETH

LINK: https://www.linkedin.com/posts/ebonica-saleth-92b268224_datascience-careergrowth-codecrafters-activity-7135929515263852544-1VCK

3. MOBILE PRICE CLASSIFICATION USING SUPPORT VECTOR MACHINE

This project develops a machine learning model to categorize mobile phones by price based on specifications. It involves data collection, preprocessing, and SVM model training with hyperparameter tuning. The model's performance is evaluated, and the final version is deployed for practical use. Comprehensive documentation highlights the SVM model's real-world application in predicting mobile phone prices.

GITHUB LINK: https://github.com/Ebonica/CODE-CRAFTERS-DATA-SCIENCE-EBONICA-SALETH

LINKEDIN LINK: https://www.linkedin.com/posts/ebonica-saleth-92b268224_datascience-careergrowth-codecrafters-activity-7135935579430522880-Xpfx

4. BREAST CANCER PREDICTION

This project uses data science to build a precise predictive model for early breast cancer detection. Leveraging patient data, it employs machine learning algorithms like logistic regression or decision trees. The goal is to create a deployable tool aiding healthcare professionals in timely identification, enhancing patient outcomes. Ethical considerations include addressing biases and ensuring data privacy. Tools: Python, Scikit-learn, and potentially TensorFlow or PyTorch for deep learning.

GITHUB LINK: https://github.com/Ebonica/EBONICA-SALETH-CVIP-Data-Science-

LINKEDIN LINK: https://www.linkedin.com/posts/ebonica-saleth-92b268224_datascience-breastcancerprediction-coderscave-activity-7103067516272332801-ffB3