KMITL
Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/123456789/1
Browse
2 results
Search Results
- Some of the metrics are blocked by yourconsent settings
Item type:Publication, Applying Convolutional Neural Network with Candlestick Images to Predict Corn Price Movement(2025-01-01)Chaiwuttisak, PornpimolThe objective of this research is to study the effect of hyperparameters on corn price movement prediction models, namely batch size and learning rate, and create a model to predict the corn price movement in the Chicago Board of Trade (CBOT) based on candlestick images at 5-day and 20-day timeframes. The data are split into three sets, namely, training set, validation set, and test set, with a ratio of 70:10:20. The models presented in this research are CNN, VGG-16, and Efficientnet-B0, which must be fine-tuned. The study’s findings on hyperparameter values within a 5-day timeframe revealed that the optimal batch size and learning rates for all three models were a batch size of 16 with a learning rate of 0.001 and a timeframe of 20 days with a dataset size of 16. However, the suitable learning rate for the CNN model was 0.001, while for the VGG-16 and EfficientNet-B0 models, it was 0.0001. Subsequently, the hyperparameter values were fine-tuned for each model and tested the model with the test set. The study findings revealed that at the 5-day timeframe, the customized CNN model outperformed other models in predicting corn price movement, with an accuracy of 55.39%, while at a 20- day timeframe, the model with the highest accuracy was EfficientNet-B0, with an accuracy of 55.03%. - Some of the metrics are blocked by yourconsent settings
Item type:Publication, Predicting the Workload in Debt Collections to Improve the Efficiency of Manpower Planning(2023-01-01)Chaiwuttisak, PornpimolThis research aimed to predict volume workloads in debt collections and compare the accuracy of forecasting methods. Three forecasting methods were considered in the study: the SARIMA model, the random forest model, and long short-term memory. The data used in this study were a time series of a daily debt collection volume workload due 1, 5, 10, 15, 20, and 25 in the used car loan corporation. They were divided into 2 datasets. The first dataset containing the past data from June 2020 to October 2020 was used for selecting the most suitable model, and the second dataset containing the past data from November 2020 to December 2020 was used for comparing the prediction accuracy of each forecasting model in terms of mean absolute percentage error (MAPE). Consequently, the lowest MAPE achieved by LSTM for different due dates was 6.79%, 6.24%, 7.08%, 10.88%, 12.45%, 10.17%, respectively, while the MAPE achieved by random forest was 11.72%, 11.27%, 8.94%, 11.92%, 13.91%, 16.67%, respectively, and the MAPE achieved by SARIMA was 23.35%, 32.87%, 32.58%, 30.07%, 33.93%, 27.31%, respectively. It indicates that the LSTM model was the most accurate to forecast the daily debt collection volume workload of the field debt collector in advance of the future. The predicted workload can be used as a piece of supporting information for adequate workforce planning of the corporation’s used car loan.