👩‍💻 Results-Oriented Analyst with a Focus on Data-Driven Decision Making and Predictive Analytics 👩‍💻

🌍 As a Professional Data Scientist, I specialize in data preprocessing, imputation, wrangling, and transforming data into actionable insights. I also develop robust machine learning models.
🎨 I tackle diverse projects, analyzing complex business challenges and delivering strategic recommendations.
📚 Feel free to explore my repositories to discover the projects I've completed.
💡 Connect with me through my portfolio and LinkedIn. Let's collaborate and innovate together! 😄

🔥 Actively open for Data Analyst, Business Analyst / Business Intelligence, and Data Scientist Role
🔥 Further learning on AI & Machine Learning

✅ Improving Employee Retention by Predicting Employee Attrition Link Project
Enhancing employee retention by developing a predictive model to identify employees who are at risk of leaving the company. By analyzing various HR data points and employee behavior patterns, the model helps organizations proactively address attrition issues, improve workforce stability, and reduce recruitment costs. The project includes data preprocessing, feature engineering, model training, and evaluation, with the goal of providing actionable insights for HR management.

✅ Analyze Customer Personality to Enhance Marketing Campaigns Using Machine Learning Clustering: Link Project
Creating customer personality using Machine Learning resulting 4 type of customers consist of: Cluster 0 (Middle-Low Income & Low Spend), Cluster 1 (Low Income & Spend), Cluster 2 (Middle-high Income & High Spend), and Cluster 3 (High Income & Spend).

✅ Performance Marketing Dashboard Kimia Farma 2020 - 2023 (Project Based Intern Kimia Farma with Rakamin): Link Project
Designing and developing an interactive performance marketing dashboard using Tableau, covering data from 2020 to 2023. The dashboard visualizes key marketing metrics such as campaign performance, ROI, conversion rates, and customer engagement over time. It enables marketing teams to monitor trends, identify successful strategies, and make data-driven decisions to optimize future campaigns.

✅ Retail Commerce Transaction Dashboard (2020-2023) – Looker Studio: Link Project
This project involves designing an interactive dashboard using Looker Studio to visualize key retail commerce metrics from 2020 to 2023. The dashboard provides insights into sales trends, revenue by product category, payment method usage, quantity sold by category, and discount amounts. It also includes detailed summaries of products, categories, and customers, enabling stakeholders to monitor performance, identify growth opportunities, and make data-driven decisions to optimize retail operations.

✅ Predict Customer Clicked Ads Classification by Using Machine Learning: Link Project
Deveoped Logistic Regression model (Standardized) with score on Accuracy: 0.9767, precision: 0.993, and recall: 0.9600 with the best features: Daily Time Spent on Site, Daily Internet Usage, Area income, and Age, suggesting to Retargeting marketing on middle-aged adults customers (35 - 50 years old) with typical middle-lower income and spent less on site and internet.

✅ Analyzing Default Risk on Home Credit (Project Based Intern Home Credit with Rakamin): Link Project
In collaboration with Home Credit and Rakamin, I analyzed default rates and predicted customer risk profiles. Utilizing algorithms like Logistic Regression, Decision Tree, Random Forest, AdaBoost, and XGBoost, the Logistic Regression model achieved the best performance with an ROC AUC score of 0.74.

✅ Creating a Model for Credit Risk Prediction (Project Based Intern IDX Partners with Rakamin): Link Project
Developed a credit risk prediction system to evaluate loan default probabilities, aimed at automating financial risk assessments for ID/X Partners. Performed comprehensive data preparation and transformation to optimize datasets for machine learning. Employed Logistic Regression to build the model, achieving high performance metrics. Delivered a model with an ROC-AUC of 92% and recall of 89%, enabling precise and automated credit risk evaluation.

✅ Analyzing Shopping Cart: Link Project
Analyzing shopping cart data from Australian retail transactions to uncover customer purchasing patterns and trends. By exploring the data through statistical analysis and visualization techniques, the project aims to provide insights into consumer behavior, popular product combinations, and seasonal variations. These findings can help retailers optimize inventory management, marketing strategies, and improve overall customer experience.

📜 Dashboarding with Google Looker Studio (Project Based Intern Bank Muamalat with Rakamin)

⚡️Programming Language: Python.
⚡️Data Manipulation and Analysis: Pandas, Numpy, PySpark.
⚡️Data Visualization: Matplotlib, Seaborn, Looker Studio, Tableau, Power BI.
⚡️Machine Learning: Scikit-learn, Regression, Classification, Unspervised Learning.
⚡️Databases: MySQL, PostgreSQL, DBeaver.
⚡️Statistical Analysis: Hyphothesis testing, Regression Analysis.
⚡️Other: Git, A/B Testing.