No abstract

Collecting and mining customer consumption data are crucial to assess customer value and predict customer consumption behaviors. This paper proposes a new procedure, based on an improved Random Forest Model by: adding a new indicator, joining the RFMS-based method to a K-means algorithm with the Entropy Weight Method applied in computing the customer value index, classifying customers to different categories, and then constructing a consumption forecasting model whose RMSE is the smallest in all kinds of data mining models. The results show that identifying customers by this improved RMF model and customer value index facilitates customer profiling, and forecasting customer consumption enables the development of more precise marketing strategies.

UNSTRUCTURED Visual fatigue is a major challenge as mobile phones and monitors become more popular. The paper proposed a solution to EEG-based visual fatigue detection device at home, with cloud servers and relative health centers for further data analysis through Internet of Things. To realize real-time EEG detection, preprocessing paths and comparison of commonly used machine-learning algorithms are evaluated based on their accuracy and efficiency. Among all of the algorithms, Random Forest proves to have the best accuracy with comparatively small computation. By applying statistical analysis into the gathered data in Random Forest model, it’s then found that α channel has the strongest relationship with predicting results. It’s also among several EEG rhythms which change with little connections to the location of electrodes. These findings offer insights into building high-efficiency and real-time EEG detectors integrated in wearable devices as well as smart medical systems.