Claim Missing Document
Check
Articles

Found 3 Documents
Search

Factors Affecting Online Purchase Intention on Social Media Users During the Pandemic in Jakarta Muhammad Sadat, Andi; Saidani, Basrah; Sholikhah; Prompreing, Kattareeya
GREENOMIKA Vol. 5 No. 2 (2023): GREENOMIKA
Publisher : Universitas Nahdlatul Ulama Sidoarjo

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55732/unu.gnk.2023.05.2.1

Abstract

This study analyzes the factors influencing online purchase intention among social media users in Jakarta during the Covid-19 pandemic. In the literature, many variables can be used to explain the phenomenon of online purchases. However, this research is limited to the main variables such as social media marketing, customer trust, e-Word of mouth, brand image, and online customer reviews. The data collection method was carried out through a questionnaire with a purposive sampling technique via a google form, which was distributed using social media networks, namely WhatsApp group and Facebook, which are popular platforms in the country. The relationship of each independent variable to the dependent variable was tested using the structural equation modeling (SEM) technique using Smart PLS version 3. A total of 238 sample units spread across the DKI Jakarta area were successfully collected and processed. The results of the data analysis show that of the five hypotheses proposed, only one is significant, namely, online customer reviews have a significant relationship to online purchase intention during the Covid-19 pandemic in DKI Jakarta.
Evaluating the Influence of Economic Indicators on Country Risk Premiums Using Random Forest: A Comprehensive Study on Global Country Data Prompreing, Kattareeya
Journal of Current Research in Blockchain Vol. 2 No. 2 (2025): Regular Issue June 2025
Publisher : Bright Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jcrb.v2i2.32

Abstract

This study investigates the relationships between key macroeconomic indicators—Gross Domestic Product (GDP), Unemployment Rate, and Country Risk Premium—using a combination of correlation analysis, Random Forest Regression, and data visualization techniques. The correlation matrix revealed a weak negative relationship between GDP and Country Risk Premium (r = -0.19), suggesting that economic prosperity modestly reduces perceived investment risk. Conversely, Unemployment Rate exhibited a very weak positive correlation with Country Risk Premium (r = 0.065), indicating that labor market instability may slightly increase financial risk. The Random Forest model achieved a mean squared error (MSE) of 2.55 and an R-squared value of 0.018, highlighting the limited predictive power of GDP and Unemployment Rate alone. Feature importance analysis showed that GDP accounted for 53.7% of the model's predictive power, while Unemployment Rate contributed 46.3%, underscoring the relevance of both variables. Visualizations, including scatter plots and boxplots, provided further insights into the variability and complexity of Country Risk Premium. The findings suggest that while GDP and Unemployment Rate are important predictors, additional factors such as political stability or inflation rates may be necessary to improve predictive accuracy. This study contributes to the understanding of financial risk determinants and highlights the potential of advanced modeling techniques in economic research.
Predicting Player Performance in EA SPORTS FC 25: A Comparative Analysis of Linear Regression and Random Forest Regression Using In-Game Attributes Prompreing, Kattareeya
International Journal Research on Metaverse Vol. 2 No. 1 (2025): Regular Issue March
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/ijrm.v2i1.22

Abstract

This study presents a comparative analysis of Linear Regression and Random Forest Regression models to predict player performance in EA SPORTS FC 25 using in-game attributes. The primary objective is to evaluate these models in terms of their accuracy and effectiveness in predicting player ratings based on key attributes like Ball Control, Dribbling, Defense, and Reactions. The dataset comprises 17,737 player records with multiple performance indicators, preprocessed to ensure quality data for modeling. The research process involves data exploration, model development, and evaluation using metrics such as Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R²). Results indicate that the Random Forest model outperforms the Linear Regression model, achieving a lower MAE and RMSE, and a higher R² score, highlighting its ability to capture complex, non-linear relationships among player attributes. The study’s findings underscore the significance of ensemble models in gaming analytics and provide insights for gamers and developers to optimize gameplay strategies and improve game mechanics. Limitations include data constraints, and recommendations for future research suggest incorporating more diverse player data and exploring advanced algorithms.