“A picture is worth a thousand words”: Never has this adage been more meaningful than it is today. Online social media is driving the growth of unstructured image data. Unstructured data must be structured to be informative and thereby contribute to user understanding and revenue generation. Hitherto, companies have only been able to accomplish this through tedious manual work. This paper demonstrates how image data can be analyzed automatically using a combination of image analysis methods and fuzzy cluster algorithms to predict user preferences, which companies can then use to make targeted offers. Several methods, including support vector machines (SVMs) and convolutional neural networks (CNNs), are benchmarked across various cases of image data taken from an online travel community. Depending on the images’ diversity either a SVM or a CNN provides the best basis for preference prediction.

“一张图胜千言”：这句格言从未像今天这样有意义。在线社交媒体正在推动非结构化图像数据的增长。非结构化数据必须结构化以提供信息，从而有助于用户理解和创收。迄今为止，公司只能通过繁琐的手工工作来实现这一点。本文演示了如何使用图像分析方法和模糊聚类算法的组合自动分析图像数据以预测用户偏好，然后公司可以使用这些偏好来提供有针对性的报价。包括支持向量机 (SVM) 和卷积神经网络 (CNN) 在内的几种方法在从在线旅游社区获取的各种图像数据案例中进行了基准测试。