Abstract: The main goal of the thesis, titled "Predictive Analysis on the Commercial Success of Game," is to predict whether a game will be successful or not after being published by analyzing previous game sale data. Whether a game is considered a hit or not is determined by the number of game copies sold. Previous game sale data were collected from the website Kaggle, Meta critics and Gamespot. The attribute global sale was correlated with all other attributes from the dataset. This enabled the identification of trend lines and determination of the attributes that have the most impact on global sales. Prediction was carried out using Random Forest Classifier and Logistic Regression. One Hot Encoding was used as LR and RFC cannot work with string value.

Works Cited:

Sheikh Arafat Rahman Shovo, ShafiulAlam, Shaikh Shariful Habib " Predictive Analysis on Commercial Success of Game", IARJSET International Advanced Research Journal in Science, Engineering and Technology, vol. 10, no. 5, pp. 284-294, 2023. Crossref https://doi.org/10.17148/IARJSET.2023.10536

| DOI: 10.17148/IARJSET.2023.10536