Data Analyst with 1+ years in machine learning and data analysis.
AI is analyzing your overall score…
Identifying your key strengths…
Evaluating your skill match against the job requirements…
Assessing your cultural and operational fit
Data Science enthusiast with a strong foundation in statistics and proven experience in developing machine learning models on large-scale datasets (6,000,000 + records). Built end-to-end solutions including fraud detection (95% accuracy), customer churn prediction, and LSTM-based forecasting models. Proficient in Python, SQL, and data visualization, with a strong ability to translate data into impactful business insights.
Universitas Negeri Jakarta
Undergraduate Student · Major Statistic
August 1, 2022 – Present
Badan Perwakilan Mahasiswa
Staff Badan Aspirasi Mahasiswa
February 1, 2024 – February 1, 2025
Jakarta, Jakarta, Indonesia
Badan Pusat Statistik
Data Provision and Content Division (Statistics Service Team)
October 1, 2023 – April 1, 2025
Jakarta, Jakarta, Indonesia
Lembaga Legislatif Mahasiswa
Staff Humas
January 1, 2023 – January 1, 2024
Jakarta, Jakarta, Indonesia
Customer Churn Prediction (Machine Learning)
June 1, 2026 – Present
Developed and evaluated machine learning models to predict customer churn in subscription services using the Telco Customer Churn dataset. Focused on improving recall for churn class to better identify customers at risk of leaving Processed and analyzed 7,000+ customer records including categorical and numerical features. Perform data preprocessing (handling 100% missing values, encoding 15+ categorical variables, numeric scaling). Built and compared models using Logistic Regression. Improved recall for churn class from 55% to 79% (+24%) after applying SMOTE, increasing detection of 220+ additional churn customers. Achieved overall model performance of 74–77% accuracy with balanced precision and recall.
View ProjectApple Price Forecasting Using LSTM (Deep Learning)
June 1, 2026 – Present
Designed and implemented a deep learning-based forecasting model to predict Apple price trends using 2,000+ daily data points (2018 – April 2026). Applied advanced preprocessing and sequence modeling techniques, including normalization and sliding window feature engineering. Developed a stacked LSTM architecture to learn complex temporal dependencies in highly volatile cryptocurrency markets. Evaluated model performance using RMSE, ensuring reliable prediction accuracy. Created data visualizations comparing training, validation, and predicted values, demonstrating strong trend alignment between predicted and actual prices. Delivered insights on price movement patterns and volatility behavior, highlighting both model strengths and limitations. Showcased ability to translate raw financial data into actionable insights using machine learning
View ProjectFraud Detection System Using Machine Learning (Imbalanced Data Classification)
June 1, 2026 – Present
Designed and implemented a machine learning model to detect fraudulent transactions using 6.3M+ records with 11 features. Processed and analyzed 6.3M+ transactional records, enabling large-scale fraud detection modeling. Achieved 95% accuracy, while conducting deeper evaluation using precision, recall, and F1-score due to class imbalance. Identified critical limitations where fraud class recall is high, but precision is low, highlighting false positive challenges. Demonstrated understanding of imbalanced dataset problems and the importance of evaluation beyond accuracy. Provided insights into model reliability and real-world applicability in financial fraud detection systems. Showcased strong skills in machine learning, classification, and large-scale data processing
View ProjectPython 101 for Data Science Student
IBM SkillsBuild
June 1, 2026 – Present
Intro to Data Analytics
Revo U
June 1, 2025 – Present
Mini Bootcamp: Introduction to Data Analytics Batch 6
DQLab
June 1, 2025 – Present
Cultural Fit Analysis
The candidate's project diversity, ranging from customer churn prediction to financial fraud detection and price forecasting, shows a broad interest in applying data analysis to various domains. Their involvement in student organizations and internships demonstrates a proactive and collaborative attitude. The academic focus on statistics and data science aligns well with a data-driven culture. However, the experience is largely academic and volunteer-based, and while it shows initiative, it lacks direct corporate experience which might require adaptation to a more structured and commercially driven environment. The candidate's current student status and GPA indicate a commitment to learning and academic rigor.
Soft Skills & Operational Fit
The candidate demonstrates good soft skills through their involvement in student organizations, including public relations and student representation roles. This indicates teamwork, communication, adaptability, and organizational skills. Their experience in developing infographics and presenting data suggests an ability to communicate complex information clearly. The internship at Badan Pusat Statistik further highlights their ability to collaborate and enhance data literacy. However, the experience is primarily academic and organizational, with limited exposure to fast-paced corporate environments, which might require some operational adjustment.