Classification and Prediction on Rural Property Mortgage Data with Three Data Mining Methods

The Farmers Property Mortgage Policy is a strategic financial policy in western China, a relatively underdeveloped region. Many contradictions and conflicts exist in the process between the strong demand for the loans by farmers and the strict risk control by the financial institutions. The rural finance corporations should use scientific analysis and investigation of the potential households for overall evaluation of the customers. These include historical credit rating, present family situation, and other related information. Three different data mining methods were applied in this paper to the specifically-collected household data. The objective was to study which factor could be the most important in determining loan demand for households, and in the meanwhile, to classify and predict the possibility of loan demand for the potential customers. The results obtained from the three methods indicated the similar outputs, income level, land area, the way of loan, and the understanding of policy were four main factors which decided the probability of one specific farmer applying for a credit loan. The results also embodied the difference within the three methods for classifying and predicting the loan anticipation for the testing households. The artificial neural network model had the highest accuracy of 91.4 which is better than the other two methods.

Rich-text document styling restoration via reinforcement learning

Richly formatted documents,such as financial disclosures,scientific articles,government regulations,widely exist on Web.However,since most of these documents are only for public reading,the styling information inside them is usually missing,making them improper or even burdensome to be displayed and edited in different formats and platforms.In this study we formulate the task of document styling restoration as an optimization problem,which aims to identify the styling settings on the document elements,e.g.,lines,table cells,text,so that rendering with the output styling settings results in a document,where each element inside it holds the(closely)exact position with the one in the original document.Considering that each styling setting is a decision,this problem can be transformed as a multi-step decision-making task over all the document elements,and then be solved by reinforcement learning.Specifically,Monte-Carlo Tree Search(MCTS)is leveraged to explore the different styling settings,and the policy function is learnt under the supervision of the delayed rewards.As a case study,we restore the styling information inside tables,where structural and functional data in the documents are usually presented.Experiment shows that,our best reinforcement method successfully restores the stylings in 87.65%of the tables,with 25.75%absolute improvement over the greedymethod.We also discuss the tradeoff between the inference time and restoration success rate,and argue that although the reinforcement methods cannot be used in real-time scenarios,it is suitable for the offline tasks with high-quality requirement.Finally,this model has been applied in a PDF parser to support cross-format display.