Research on Big Data Processing Based on Machine Learning in Market Trend Prediction Model

This paper proposes a new Gradient Boosting Component-decision (GBC-D) model, which combines the advantages of Markov Decision process (MDP), gradient lifting tree (GBT) and principal Component analysis (PCA). Applied to big data processing is based on machine learning in market trend prediction model research. The GBC-D model uses PCA for data reduction and feature extraction, which reduces the computation and preserves the main features of the data. MDP is used to describe the market state transition process and maximize the expected cumulative return by optimizing the decision sequence. GBT is introduced as a forecasting model to gradually improve the forecasting performance to predict market trends more accurately. Combining the advantages of the three methods, the model can effectively deal with the complexity and uncertainty in big data and improve the accuracy and stability of market trend prediction. In the experimental part, we compared the BGC-D with the traditional prediction model. The results show that GBC-D can reduce the prediction error in the complex and changeable market environment, capture the market dynamics more accurately, and improve the overall performance of the system. This fully validates the feasibility and effectiveness of GBC-D architecture in big data processing market trend prediction.