Passionate in AI. My experience includes presenting my research on conference and internship

github

Galih Kusuma Wijaya  • Peerlist

- Model Performance: Achieved an R² score of 0.96 and RMSE of 0.7048, highlighting the model's precision and reliability in forecasting economic trends. - Data Integration: Incorporated macroeconomic factors like inflation and interest rates to enhance prediction accuracy, supported by comprehensive historical data analysis. - Comparison Insights: Provided predictions closely aligned with economic forecasts, deviating only 0.10% from leading expert estimates, reinforcing model validity. - Implications for Policy: Offered valuable insights for economic planners and policymakers to optimize GDP growth, supporting evidence-based decision-making.

Economic Growth Forecasting: Predicted Indone

Food price volatility is a persistent issue affecting consumer purchasing power, market stability, and policy decisions. Our study investigates how XGBoost, optimized with Random Search, improves the accuracy of food price predictions. Key Insights: - Feature Selection is Crucial: Time-based features such as lagged prices and seasonal trends significantly improve model performance. - Hyperparameter Optimization Matters: Random Search tuning reduced the Mean Absolute Percentage Error (MAPE) to 0.0131, outperforming default settings. - Ensemble Models Are More Effective: XGBoost and Random Forest demonstrated better performance in capturing price fluctuations compared to ARIMA. - Computation vs. Accuracy Trade-off: While XGBoost provided the best accuracy, it required more computational time compared to CatBoost and Random Forest. These findings demonstrate how machine learning can enhance economic forecasting, helping policymakers and industry stakeholders develop better strategies for price stability.

Optimizing XGBoost Model with Random Search f

- Performing analysis stages using Python from data gathering to data visualization. - Determining the city with the highest user purchases for a specific product. - Identifying the product category with the highest sales. - Analyzing the difference in sales of a product from year to year.

Product Sales Analysis Based on Cities and Re

- Sentiment Analysis Implementation: Conducted a comprehensive sentiment analysis of public perception regarding the Jabodetabek LRT project using machine learning techniques, specifically employing the TextBlob library. - Model Evaluation: Achieved a model accuracy of 90.35%, with detailed performance metrics including precision, recall, and F1-scores for sentiment categories (positive, neutral, negative), demonstrating strong predictive capabilities. - Data Visualization: Created informative visualizations, including pie charts, to effectively communicate sentiment distribution and insights derived from the analysis to publics. - Insights for Publics: Provided actionable insights for policymakers and transportation authorities based on public sentiment, helping to identify areas for improvement in the LRT services and enhance public satisfaction.

Sentiment Analysis of Public Perception towar

- Analyzing Type 1 Diabetes, an autoimmune disorder often affecting children and teenagers. - Conducting an age category analysis, categorizing patients into different age groups to gain insights. - Highlighting key findings, including the average age of Type 1 Diabetes patients and the importance of early awareness. - Providing recommendations for promoting healthy eating habits and regular health check-ups, especially for children and teenagers at risk of Type 1 Diabetes. Concluding the analysis with a call to action for a healthier future. - Creating a dashboard to visualize the distribution of Type 1 Diabetes patients based on age groups.