As one of the financial industries, the insurance industry is now facing a vast market and significant growth opportunities. The insurance company will generate a lot transaction data each day, thus forming a huge database. Recommending insurance products for customers accurately and efficiently can help to improve the competitiveness of insurance company. Data mining technologies such as association rules have been applied to the recommendation of insurance products. However, large policyholders’ data will be calculated when it being processed with associate rule algorithm. It not only requires higher cost of time and space, but also can lead to the final rules lack of accuracy and differentiation. In this paper, a recommendation model for insurance products based on consumer segmentation is constructed, which first divides consumer group into different classes and then processed with associate rule algorithm. The empirical results show that our proposed method not only makes the consumption of association rules analysis reduced, it has also got more effective product recommendation results.

Zhiwei Li, Ran Song, Caihong Sun, Wei Xu, Zhengtao Yu, Ji-Rong Wen. Findings of the Association for Computational Linguistics ACL 2024. 2024.

Particulate matter PM_2.5 pollution affects the Chinese population, particularly in cities such as Shenyang in northeastern China, which occupies a number of traditional heavy industries. This paper proposes a semi-supervised learning model used for predicting PM_2.5 concentrations. The model incorporates rich data from the real world, including 11 air quality monitoring stations in Shenyang and nearby cities. There are three types of data: air monitoring, meteorological data, and spatiotemporal information (such as the spatiotemporal effects of PM_2.5 emissions and diffusion across different geographical regions). The model consists of two classifiers: genetic programming (GP) to forecast PM_2.5 concentrations and support vector classification (SVC) to predict trends. The experimental results show that the proposed model performs better than baseline models in accuracy, including 3% to 18% over a classic multivariate linear regression (MLR), 1% to 11% over a multi-layer perceptron neural network (MLP-ANN), and 21% to 68% over a support vector regression (SVR). Furthermore, the proposed GP approach provides an intuitive contribution analysis of factors for PM_2.5 concentrations. The data of backtracking points adjacent to other monitoring stations are critical in forecasting shorter time intervals (1 h). Wind speeds are more important in longer intervals (6 and 24 h).