No abstract

No abstract

The amount of data stored by banks is rapidly increasing and provides the opportunity for banks to conduct predictive analytics and enhance its businesses. However, data scientists are facing large challenges, handling the massive amount of data efficiently and generating insights with real business value. In this paper, the Intelligent Customer Analytics for Recognition and Exploration (iCARE) framework is presented to analyze banking customer behaviors from banking big data, through analytical modeling methodologies and techniques designed for a key business scenario. Combining IBM software platforms and big data processing power with customized data analytical models, the iCARE solution provides deeper customer insights to satisfy a bank's specific business need and data environment. The advantages of the iCARE framework have been confirmed in a real case study of a bank in southeast China. In this case, iCARE helps generate insights for active customers based on their transaction behavior, using close to 20 terabytes of data.

No abstract

Query segmentation is essential to query processing. It aims to tokenize query words into several semantic segments and help the search engine to improve the precision of retrieval. In this paper, we present a novel unsupervised learning approach to query segmentation based on principal eigenspace similarity of queryword-frequency matrix derived from web statistics. Experimental results show that our approach could achieve superior performance of 35.8% and 17.7% in Fmeasure over the two baselines respectively, i.e. MI (Mutual Information) approach and EM optimization approach.