This paper is based on the 3rd place solution to IEEE BigData Cup 2021: RL based RecSys. Standing on the competition task of game-like multi-step recommendation, we have analyzed user data and task goals, and treated recommendation task as multi-classification. After comparing different models, the LightGBM multi-classification model is finally selected. In addition, we evaluate those features that potentially cause the greatest impact on the prediction of our model, making it possible to predict the users’ purchase sequence accurately.