Skip to content
View praditaw's full-sized avatar
6 followers · 6 following

Block or report praditaw

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Maximum 250 characters. Please don't include any personal information such as legal names or email addresses. Markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
praditaw/README.md

Hi there 👋, I'm Pradita Ajeng Wiguna

linkedin-pradita google-scholar-pradita

A passionate Physics graduate with a strong interest in data and technology. I recently completed the Hacktiv8 Full Time Data Science bootcamp, where I gained hands-on experience in Python, SQL, exploratory data analysis (EDA), machine learning, and data visualization. My academic and research experience has developed my ability to analyze data, identify patterns, solve problems critically, and communicate insights effectively. I am eager to apply these skills in data-related roles to support data-driven decisions and create meaningful business impact.

🚀 Featured End-to-End Projects

Here are some of the key projects I've developed:

📞 Clusturn: Predicting & Clustering Churn Customers

  • Description: This end-to-end data project was developed to proactively predict customer churn in the telecommunications sector. The system uses a classification model to identify high-risk customers and a clustering model to understand the root causes of their dissatisfaction. The insights generated enable personalized, cost-effective retention strategies, protecting revenue by preventing customer loss.
  • Tech Stack: Python, Pandas, Scikit-learn, Imblearn, K-modes, Matplotlib, Seaborn, Pickle, Streamlit.

🏥 Predictive Modeling for Hospital Length of Stay (LoS)

  • Description: I developed and deployed an end-to-end machine learning project to predict patient Length of Stay (LoS) and provide data-driven insights for improving hospital operational efficiency. After performing comprehensive EDA, feature engineering, and hyperparameter tuning, the final benchmark model achieved a test MAE of ~1.19 days. A key strategic recommendation was to prioritize clinical data enrichment for future model enhancements.
  • Proof-of-Concept: A functional inference application was built using Streamlit and deployed on Hugging Face Spaces.
  • Tech Stack: Python, Pandas, NumPy, Scikit-learn, Phik, feature-engine, Streamlit, Hugging Face Spaces, Matplotlib, and Seaborn.

🛒 Optimizing Retail Profitability: A Supermarket Sales Performance Analysis

  • Description: This end-to-end project was developed to analyze supermarket sales transactions to identify key drivers of profitability. The solution features an automated ETL pipeline and an interactive dashboard, providing actionable recommendations for optimizing product strategy, branch performance, and customer engagement to increase gross income.
  • Tech Stack: Python, Pandas, PostgreSQL, Apache Airflow, Elasticsearch, Kibana, Great Expectations, and Docker.

🎵 Data-Driven Insights: Global Music Streaming Trends

  • Description: This analysis was conducted to gain insight into global music streaming trends and differences in user preferences. The insights generated from this project are aimed at supporting strategic decision-making within the digital music industry.
  • Tech Stack: Tableau, Python, Pandas, Seaborn, Matplotlib, and SciPy.

🛠️ Languages and Tools

Here are some of the technologies I work with:

Programming & Databases:

python postgresql

Data Science & Machine Learning Libraries:

pandas scikit-learn tensorflow matplotlib seaborn streamlit

Tools & Environments:

tableau git github airflow docker huggingface gcp

🎓 Academic Background & Research

My academic foundation includes a Master of Science in Physics from Universitas Indonesia and a Bachelor of Science in Physics from Universitas Negeri Semarang. During my academic career, I have authored and co-authored multiple scientific papers and participated in national and international conferences.

You can find my research work on:

Let’s connect—I'm always open to learning, collaborating, and growing in the data field.

Pinned Loading

  1. customer-churn-prediction-and-clustering customer-churn-prediction-and-clustering Public

    Forked from FTDS-assignment-bay/p2-final-project-ftds-042-rmt-group-002

    Developing a proactive system for the telecom sector that predicts customer churn and segment at-risk users through predictive modeling and clustering.

    Jupyter Notebook

  2. patient-los-prediction patient-los-prediction Public

    Predicting patient Length of Stay (LoS) using machine learning to provide insights for hospital operational efficiency.

    Jupyter Notebook

  3. supermarket-sales-analysis-pipeline supermarket-sales-analysis-pipeline Public

    An end-to-end data pipeline that analyzes supermarket sales to provide actionable insights for increasing profitability.

    Jupyter Notebook

  4. global-music-streaming-trends-analysis global-music-streaming-trends-analysis Public

    Data-driven analysis exploring global music streaming trends and listener preferences to support strategic decision-making in the digital music industry.

    Jupyter Notebook