Improving Sports Outcome Prediction Process Using Integrating Adaptive Weighted Features and Machine Learning Techniques

Enhancing Basketball Game Outcome Prediction through Fused Graph Convolutional Networks and Random Forest Algorithm

Basketball is a popular sport worldwide, and many researchers have utilized various machine learning models to predict the outcome of basketball games. However, prior research has primarily focused on traditional machine learning models. Furthermore, models that rely on vector inputs tend to ignore the intricate interactions between teams and the spatial structure of the league. Therefore, this study aimed to apply graph neural networks to basketball game outcome prediction, by transforming structured data into unstructured graphs, to represent the interactions between teams in the 2012-2018 NBA season dataset. Initially, the study used a homogeneous network and undirected graph to build a team representation graph. The constructed graph was fed into a graph convolutional network, which yielded an average success rate of 66.90% in predicting the outcome of games. To improve the prediction success rate, feature extraction based on the random forest algorithm was combined with the model. The fused model yielded the best results, and the prediction accuracy was improved to 71.54%. Additionally, the study compared the results of the developed model with previous studies and the baseline model. Our proposed method considers the spatial structure of teams and the interaction between teams, resulting in superior performance in basketball game outcome prediction. The results of this study provide valuable insights for basketball performance prediction research.

Special Issue on Recent Advances in Machine Learning and Applications

Digital technologies for cyber-physical systems are rapidly advancing, and the ubiquity of the Internet of Things (IoT) has created significant challenges for academic, industrial, and service applications due to high dimensionality, noise contamination, incompleteness, inconsistency, and massive amounts of data [...]

Machine-Learning-Based System for the Detection of Entanglement in Dyeing and Finishing Processes

Many dyeing and finishing factories generally use old-fashioned dyeing machines. A key issue when using these machines is that the dyeing tank cannot detect entanglement problems, which may result in a lower dyeing quality. In this paper, imbalanced data with ensemble machine learning, such as Extreme Gradient Boosting (XGBoost) and random forest (RF), are integrated to predict the possible states of a dyeing machine, including normal operation, entanglement warning, and entanglement occurrence. To verify the results obtained using the proposed method, we worked with industry−academia collaborators. We collected 1,750,977 pieces of data from 1848 batches. The results obtained from the analysis show that after employing the Borderline synthetic minority oversampling technique and the Tomek link to deal with the data imbalance, combined with the model established by XGBoost, the prediction accuracy of the normal operation states, entanglement warning, and entanglement occurrence were 100%, 94%, and 96%, respectively. Finally, the proposed entanglement detection system was connected with the factory’s central control system using a web application programming interface and machine real-time operational parameter data. Thus, a real-time tangle anomaly warning and monitoring system was developed for the actual operating conditions.