<![CDATA[Decision-making based on weather factors is often subjective and inconsistent. This research applies data mining classification methods to build an objective predictive model regarding the decision to play tennis based on weather conditions. The objective of this study is to analyze the performance of the Naive Bayes algorithm in predicting this decision. The methodology involves applying the Naive Bayes algorithm to the classic "Play Tennis" dataset, which consists of 14 instances with four categorical predictor attributes: outlook, temperature, humidity, and wind. The modeling and evaluation process was conducted visually using the Altair AI Studio (RapidMiner) platform, employing the cross-validation technique to test model stability. The test results show an average model accuracy of 57.14%. A deeper analysis of the confusion matrix reveals that the model has a strong bias towards predicting the 'Yes' class, yet is very weak in identifying the 'No' class (20.00% recall). Specifically, the model exhibits a high number of False Positive errors, where 4 out of 5 'No' cases were misclassified. In conclusion, the Naive Bayes model in its current configuration is not yet fully reliable for practical application due to its biased performance. This study recommends further optimization, such as applying data balancing techniques or using more complex alternative algorithms, to significantly improve predictive performance.]]>
Copyrights © 2025
