The data story contains contention of a small part in our project. We mainly show the most representatives in our story, including descriptive statistics in both numerical and non-numerical features, review text analysis and machine learning models. There are many more details in our notebook. Several proofs have been made to verify our previous assumptions of useful features for hit movie making. However, there remain many details for improvement. For example, there is not enough data to further our hit movie analysis, and some methods and algorithms need to be improved. Anyway, we can say we find the generally intuitive features in movie industry, but many other factors always neglected should be taken into account, like title_change feature after greedy selection. Therefore, we will go into the area of further deep data analysis in the future.