Computational Finance and Business Intelligence (CFBI) Session 1

Time and Date: 9:00 - 10:40 on 14th June 2017

Room: HG D 7.1

Chair: Yong Shi

116 Improved New Word Detection Method Used in Tourism Field [abstract]
Abstract: Chinese segmentation has attracted amounts of attention in natural language processing in recent years and is the basis of web text mining. The article improved statistics-based method EMI, then we use improved approach to detect new words in tourism field. The result demonstrates that our method can detect new words significantly, especially in detecting proper nouns and sentiment words which will be helpful in subsequent tasks such as sentiment analysis and word embedding. In additional, this paper analyze parameters which are influential on the effects of new words detection. At last, the article discussed possible application of new word detection in sentiment analysis.
Wei Li, Kun Guo, Yong Shi, Luyao Zhu and Yuanchun Zheng
337 Large-scale Nonparallel Support Vector Ordinal Regression Solver [abstract]
Abstract: Large-scale linear classification is widely used in many areas. Although SVM-based models for ordinal regression problem are considered as the popular leaning techniques, their performance with kernels are often suffering from time consuming. Recently, linear SVC without kernels not only is shown to obtain competitive performance in most of the cases, but also it is considerably faster in training and testing process. However, a few studies have focused on linear SVM-based ordinal regression models. In this paper, we proposed an efficient solver for training the linear Nonparallel Support Vector Ordinal Regression based on alternating direction method of multipliers (ADMM). Our experiments show that the proposed algorithm is suitable for training large document ordinal regression and efficiently obtained desired results.
Huadong Wang, Jianyu Miao, Seyed Mojtaba Hosseini Bamakan, Lingfeng Niu and Yong Shi
164 Relationship between Capital Operation and Market Value Management of Listed Companies Based on Random Forest Algorithm [abstract]
Abstract: This paper analyzes the influence of capital operations on the performance of listed companies under different market conditions by combining various capital operation modes with the market value management. Random Forest algorithm is adopted and other machine learning methods are used to compare. We find that capital operation is significantly related to market value management and different capital operations have different effects on companies in different market conditions. In addition, Random Forest algorithm has the highest classification accuracy in different market environments and is more stable under different thresholds. Our findings will help to establish a market or industry benchmark which provides a scientific basis and decision support to the target companies when they operate their capitals.
Wen Long, Linqiu Song and Lingxiao Cui
182 A Hash Based Method for Large Scale Nonparallel Support Vector Machines Prediction [abstract]
Abstract: Recent years have witnessed more and more success of hash methods for building efficient classifiers, but less for prediction in machine learning. In this paper, we propose a hash based method for large scale nonparallel support vector machine prediction(HNPSVM). Our key idea of this method is that we use an approximal decision function instead of exact decision function by computing the Hamming distance between hashing the normal to the hyperplane of the classifier and the features. This method benefits nonparallel support vector(NPSVM) prediction in three aspects. First, it enhances the prediction accuracy using an flexible and general method. Second, the proposed HNPSVM reduce storage cost owing to the compact binary hash representation. Last, HNPSVM can speed up the computation of classification function. Moreover, we prove that the classification results of a hash based NPSVM classifier converge to the results of the exact NPSVM classifier as the number of binary hash functions tends to infinity. Several experiments on large scale data sets show the efficient of our method.
Xuchan Ju and Tianhe Wang
299 Alternating Direction Method of Multipliers for L1- and L2-norm Best Fitting Hyperplane Classifier [abstract]
Abstract: Recently, two-sided best fitting hyperplane classifier (2S-BFHC) is proposed, which has several significant advantages over previous proximal hyperplane classifiers. Moreover, Concave-Convex Procedure (CCCP) has already been provided to solve the dual problem of 2S-BFHC. In this paper, we solve the primal problem of 2S-BFHC by the alternating direction method of multipliers (ADMM) which is well suited to solve the distributed optimization problem, and we also propose a robust L1-norm two-sided best fitting hyperplane classifier (L1-2S-BFHC) with ADMM, which aims at giving a robust performance for the problem with outliers. Priliminary numerical results demonstrate the effectiveness of proposed methods.
Chen Wang, Chun-Na Li, Hua-Xin Pei, Yan-Ru Guo and Yuan-Hai Shao