Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Journal of Applied Science, Engineering, Technology, and Education

Marketing Research : The Application of Auto Sales Forecasting Software to Optimize Product Marketing Strategies Bakri, Rizal; Data, Umar; Saputra, Andika
Journal of Applied Science, Engineering, Technology, and Education Vol. 1 No. 1 (2019)
Publisher : Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (985.508 KB) | DOI: 10.35877/454RI.asci1124

Abstract

The aims of this study is to apply the Auto Sales Forecasting software to predict sales transaction data. The Auto Sales Forecasting software consists of two main features namely descriptive analysis and forcasting features along with its visualization. Forecasting methods contained in the Auto Sales Forecasting application are forecasting methods of Simple Moving Average, Robust Exponantial Smoothing, Auto ARIMA, Artificial Neural Network, Holt-Winters, and Hybrid Forecast. The Auto Sales Forecasting software can intelligently choose the best forecasting method based on RMSE values. The results showed that the Auto Sales Forecasting software successfully analyzed the sales transaction data. From the analysis it was found that there were 43 types of products produced and sold by the Futry Bakery & Cake Store. Three of them are the types of products that are most in demand by consumers, namely Sweet Bread, Maros Bread, and Traditional Cakes 3500. The best selling product type, Sweet Bread, is used to build forecasting models. The best forecasting method is the Robust Exponential Smoothing method with the smallest RMSE value of 0.83 on the variable number of sold out products. Forecasting results using the Robust Exponantial Smoothing method show that the average number of products to sell for the next seven days ranges from 116 products with a certain confidence interval value.
Marketing Research : The Application of Auto Sales Forecasting Software to Optimize Product Marketing Strategies Rizal Bakri; Umar Data; Andika Saputra
Journal of Applied Science, Engineering, Technology, and Education Vol. 1 No. 1 (2019)
Publisher : Yayasan Ahmar Cendekia Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (786.461 KB) | DOI: 10.35877/454RI.asci1124

Abstract

The aims of this study is to apply the Auto Sales Forecasting software to predict sales transaction data. The Auto Sales Forecasting software consists of two main features namely descriptive analysis and forcasting features along with its visualization. Forecasting methods contained in the Auto Sales Forecasting application are forecasting methods of Simple Moving Average, Robust Exponantial Smoothing, Auto ARIMA, Artificial Neural Network, Holt-Winters, and Hybrid Forecast. The Auto Sales Forecasting software can intelligently choose the best forecasting method based on RMSE values. The results showed that the Auto Sales Forecasting software successfully analyzed the sales transaction data. From the analysis it was found that there were 43 types of products produced and sold by the Futry Bakery & Cake Store. Three of them are the types of products that are most in demand by consumers, namely Sweet Bread, Maros Bread, and Traditional Cakes 3500. The best selling product type, Sweet Bread, is used to build forecasting models. The best forecasting method is the Robust Exponential Smoothing method with the smallest RMSE value of 0.83 on the variable number of sold out products. Forecasting results using the Robust Exponantial Smoothing method show that the average number of products to sell for the next seven days ranges from 116 products with a certain confidence interval value.
Machine Learning Algorithms with Parameter Tuning to Predict Students’ Graduation-on-time: A Case Study in Higher Education Bakri, Rizal; Astuti, Niken Probondani; Ahmar, Ansari Saleh
Journal of Applied Science, Engineering, Technology, and Education Vol. 4 No. 2 (2022)
Publisher : PT Mattawang Mediatama Solution

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35877/454RI.asci1581

Abstract

This study aims to predict a student’s graduation on time (GOT) using machine learning algorithms. We applied five different machine learning algorithms, namely Random Forest, Support Vector Machine (Linear Kernel), Support Vector Machine (Polynomial Kernel), K-Nearest Neighbors, and Naïve Bayes. These algorithms were tested using 10-fold cross validation and simulated various parameter tuning values. The results show that the Random Forest algorithm produces the best accuracy and kappa statistics values, so this algorithm is suitable for modeling predictive data of students graduating on time. This predictive model is expected to be useful for higher education management in designing their strategies to assist and improve student academic performance weaknesses in order to achieve graduation on time.