In this study, we extracted greenhouse sidewall control rules using a data mining method, based on data of time and the degree of sidewall opening, which is the main environmental management practice in greenhouses used to raise rice seedlings; the data were gathered by using an IC tag system (radio frequency identification). Decision trees were generated using the degree of sidewall opening as the target variable and weather information and growing days of seedlings as explanatory variables; rules satisfying the confidence and support constraints were extracted. Reasonable rules with high confidence and support resulted when the degree of sidewall opening was divided into three degrees. Cross-validation showed 75% correctness. Furthermore, individual rules extracted from decision trees generated using data from different parts of the day (morning, daytime, evening) had higher confidence and support than those based on whole-day data, and cross-validation showed >80% correctness. Multiple regression analysis resulted in a reasonable regression expression with a coefficient of determination of 0.7 and root mean square error of 19%. Precision of the regression was improved by analyzing data separately for of each part of day. Because many of the extracted rules were consistent with the subjective rules of farm laborers who work in the greenhouses, both decision tree analysis and multiple regression analysis had the capability of extracting the logic of workers to some extent.