Developing a prediction model for customer churn from electronic banking services using data mining

Background:Given the importance of customers as the most valuable assets of organizations,customer retention seems to be an essential,basic requirement for any organization.Banks are no exception to this rule.The competitive atmosphere within which electronic banking services are provided by different banks increases the necessity of customer retention.Methods:Being based on existing information technologies which allow one to collect data from organizations’databases,data mining introduces a powerful tool for the extraction of knowledge from huge amounts of data.In this research,the decision tree technique was applied to build a model incorporating this knowledge.Results:The results represent the characteristics of churned customers.Conclusions:Bank managers can identify churners in future using the results of decision tree.They should be provide some strategies for customers whose features are getting more likely to churner’s features.

How does a data strategy enable customer value?The case of FinTechs and traditional banks under the open finance framework

The coupling of data and digital innovation opens the way for new business in the financial services sector,where customers are placed at the centre of decisions and data can help to develop customer knowledge.To carry out our research,we adopted a multi-case study approach to explore how a data strategy is developed in the retail banking industry,together with its relationship with customer value,paying particular attention to the heterogeneity between traditional banks and financial technology companies(FinTechs).Two main points emerged from the study.Firstly,there are three possible approaches to Open Finance,which are mainly defined by their different corporate cultures,organisational configurations,technological architecture and data value.Secondly,it is not enough to be a FinTech to be best placed to exploit the market,as some traditional banks share the FinTechs’approach to Open Finance.Designing new tailored products,customising their prices and offering them over the right channels through targeted communication are all data-driven initiatives that stem from cross-or up-selling potential,core to the retail banking industry for turning a customer into a cash flow,thus enabling value to be created for customers.Our findings additionally revealed that there is a form of external information asymmetry between the customer and the bank,and that there is also an internal asymmetry between bank departments,as their visibility on information about the same customer may differ.

What explains the technical efficiency of banks in Tunisia?Evidence from a two‑stage data envelopment analysis

In this study we examine the potential determinants of technical efficiency for the Tunisian commercial banking sector over the period of 1995–2017.First,we estimate banking technical efficiency with a radial and non-radial bootstrap data envelopment analysis.For the radial technique,we use an input-oriented approach and for non-radial we use the Range Adjusted Measure(RAM).Second,we use a double bootstrapping regression technique to estimate the influence of a set of eventual determinants on technical efficiency.Finally,based on all possible regressions,we gauge the overall effect of each determinant.Our results reveal that the input-oriented and RAM approach gave somewhat similar results.We found that the return on equity,the expense to income ratio,the loan to deposit ratio,and the growth rate are insignificant to Tunisian banking technical efficiency.In particular,banking technical efficiency increases with capitalization and inflation,whereas,it decreases with size,number of bank branches,management to staff ratio,and loan to asset ratio.In addition,we identified evidence supporting the moderate success of the last decade of reforms and a noticeable one for the post-revolution reforms in helping improve banking technical efficiency.The post-revolution reforms,largely revolving around reinforcing the rules of good governance and banking supervision,coupled with the restructuring of public banks,were found to be insufficient to raise overall banking technical efficiency despite improvement in the technical efficiency of private banks.

Data envelopment analysis for scale elasticity measurement in the stochastic case:with an application to Indian banking

In the nonparametric data envelopment analysis literature,scale elasticity is evaluated in two alternative ways:using either the technical efficiency model or the cost efficiency model.This evaluation becomes problematic in several situations,for example(a)when input proportions change in the long run,(b)when inputs are heterogeneous,and(c)when firms face ex-ante price uncertainty in making their production decisions.To address these situations,a scale elasticity evaluation was performed using a value-based cost efficiency model.However,this alternative value-based scale elasticity evaluation is sensitive to the uncertainty and variability underlying input and output data.Therefore,in this study,we introduce a stochastic cost-efficiency model based on chance-constrained programming to develop a value-based measure of the scale elasticity of firms facing data uncertainty.An illustrative empirical application to the Indian banking industry comprising 71 banks for eight years(1998–2005)was made to compare inferences about their efficiency and scale properties.The key findings are as follows:First,both the deterministic model and our proposed stochastic model yield distinctly different results concerning the efficiency and scale elasticity scores at various tolerance levels of chance constraints.However,both models yield the same results at a tolerance level of 0.5,implying that the deterministic model is a special case of the stochastic model in that it reveals the same efficiency and returns to scale characterizations of banks.Second,the stochastic model generates higher efficiency scores for inefficient banks than its deterministic counterpart.Third,public banks exhibit higher efficiency than private and foreign banks.Finally,public and old private banks mostly exhibit either decreasing or constant returns to scale,whereas foreign and new private banks experience either increasing or decreasing returns to scale.Although the application of our proposed stochastic model is illustrative,it can be potentially applied to all firms in the information and distribution-intensive industry with high fixed costs,which have ample potential for reaping scale and scope benefits.

Evaluating banking efficiency with data envelopment analysis:evidence from Chongqing,P.R.China

Data envelopment analysis was applied to determine relative efficiencies of state-owned and joint-stock banks in Chongqing,P. R. China,during the years 1996 to 2000. We found that state-owned banks have low levels of efficiency when compared with joint-stock banks,but some joint-stock bank branches have low efficiency scores. Efficiency difference testing by using the Mann-Whitney rank order statistic indicates that the efficiency gap between state-owned and joint-stock banks is insignificant,which is characteristic of regional banks. We also presented some factors that may affect bank efficiency,and offer suggestions to improve bank management and efficiency.

Effectiveness of the Global Banking System in 2010： A Data Envelopment Analysis Approach

The current crisis has revealed the weaknesses of the global financial in general and its banking system in particular and puts forward a requirement for assessing the effectiveness and stability of the banking sectors across countries. Based on available data from 64 countries over the world, the author tried to evaluate the effectiveness of the banking sectors in those countries through the view point of the data envelopment analysis approach to define how the global banking systems is under the effect of the current crisis. Findings from the research showed that banking systems in advanced economies are still more effective than in developing countries. Moreover, it explained the effect of the current financial crisis, the role of public finance （and the government）, and the development of the （privately） commercial banks to the effectiveness of the banking sectors. The research also explained some determinants that can affect the effectiveness of the banking system, including inflation, bank concentration, and level of economic development.

Data Fusion with Optimized Block Kernels in LS-SVM for Protein Classification

In this work, we developed a method to efficiently optimize the kernel function for combined data of various different sources with their corresponding kernels being already available. The vectorization of the combined data is achieved by a weighted concatenation of the existing data vectors. This induces a kernel matrix composed of the existing kernels as blocks along the main diagonal, weighted according to the corresponding the subspaces span by the data. The induced block kernel matrix is optimized in the platform of least-squares support vector machines simultaneously as the LS-SVM is being trained, by solving an extended set of linear equations, other than a quadratically constrained quadratic programming as in a previous method. The method is tested on a benchmark dataset, and the performance is significantly improved from the highest ROC score 0.84 using individual data source to ROC score 0.92 with data fusion.

The Optimized Way of Commercial Bank Management under the Background of Big Data

With the advent of the era of big data,the commercial management activities of commercial banks are facing both new challenges and new development opportunities.In the increasingly fierce market competition,commercial banks must pay attention to enhance their core competitiveness,only in this way can they occupy a certain advantage in the fierce market environment.Therefore,commercial banks must accurately grasp the development opportunities brought by big data,and further strengthen the optimization of business management.The author explores and analyzes the impact of big data on commercial banks,and puts forward an effective way for commercial banks to optimize business management in the context of big data,hoping to contribute to the long-term development of commercial banks.

Credit Risk Transfer and the Performance of Commercial Banks --Based on the Panel Data

Based on the panel data, we analyze the US commercial banks＇ CRT. According to the study, we find that the introduction of CRT will increase the level of banks＇ liquid risk. The performance of bank mainly is that its supervision and review of risk will drop, based on the impact of asymmetric information, commercial Banks transfer the bad loans to investors. Through the analysis we can see that after the transfer of credit risk in commercial bank did not increase income and reduce risk. Because commercial Banks can extend more bad loans to expand its lending scale, and bad loans will increase the bank overall risk.

Study on Daily Accounting Profit Feasibility of Banking Based on Data Center

By the end of 2013, Chinese large-scaled commercial banks have basically completed the construction of IT banking system, in order to provide technical guarantee of deepening business operation and operation management reform. This indicates that our national banking industry information technology has been in a new level. This paper, based on the operation principle of commercial bank safety, liquidity and profitability, makes research on improving commercial banking profit data timeliness, accuracy, integrity and realizing daily accounting profit. According to survey, the four big banks have proposed the prospect of 2013 full scope implementing daily accounting profit. Thus, this paper, based on the profit accounting status of four big banks of data center, analyzes the feasibility of daily accounting profit and puts forward the relevant solutions.

Identification of distant co-evolving residues in antigen 85C from Mycobacterium tuberculosis using statistical coupling analysis of the esterase family proteins

A fundamental goal in cellular signaling is to understand allosteric communication, the process by which sig-nals originating at one site in a protein propagate reliably to affect distant functional sites. The general principles of protein structure that underlie this process remain unknown. Statistical coupling analysis （SCA） is a statistical technique that uses evolutionary data of a protein family to measure correlation between distant functional sites and suggests allosteric communication. In proteins, very distant and small interactions between collections of amino acids provide the communication which can be important for signaling process. In this paper, we present the SCA of protein alignment of the esterase family （pfam ID： PF00756） containing the sequence of antigen 85C secreted by Mycobacterium tuberculosis to identify a subset of interacting residues. Clustering analysis of the pairwise correlation highlighted seven important residue positions in the esterase family alignments. These resi-dues were then mapped on the crystal structure of antigen 85C （PDB ID： 1DQZ）. The mapping revealed corre-lation between 3 distant residues （Asp38, Leu123 and Met125） and suggests allosteric communication between them. This information can be used for a new drug against this fatal disease.

面向多核NUCA共享数据竞争问题的Bank一致性技术

非一致Cache体系结构(NUCA)几乎已经成为未来片上大容量cache的发展方向。多核处理器的NUCA结构中,多个处理器核对共享数据的竞争访问,可能导致数据经常处于中部的cache Bank,增加NUCA的访问延迟。本文提出支持数据副本的Bank一致性技术,通过有选择地在NUCA中为访问的处理器核创建不同的数据副本,Bank一致性技术能够缓解多核处理器对共享数据的竞争问题。本文详细地介绍了Bank一致性协议的设计方法。最后,使用全系统模拟器对8个NPB基准测试程序进行了详细评测。实验结果表明,Bank一致性技术能够有效缓解多核处理器中共享数据的竞争访问问题。相比不支持Bank一致性技术的CMP-DNUCA结构,本文的方法能将系统IPC性能平均提升5.95%。

B细胞衔接蛋白BANK在小鼠实验性自身免疫性脑脊髓炎中的作用

目的:探讨B细胞特异性衔接蛋白BANK(B cell adoptor protein with ankyrin repeats)在小鼠实验性自身免疫性脑脊髓炎(Experimental autoimmune encephalomyelitis,EAE)中的作用。方法:MOG35-55多肽免疫C57BL/6鼠和BANK缺陷(BANK-deficient,BANK-/-)鼠制备EAE模型,观察实验动物临床症状及中枢神经系统的病理学变化;提取小鼠脑组织及脾脏,经流式细胞术检测中枢神经系统及外周免疫器官中的CD4+T细胞、CD8+T细胞及调节性T细胞的变化。结果:BANK-/-鼠EAE临床症状评分明显高于C57BL/6鼠,且体重减轻明显(P<0.05);HE染色结果显示,BANK-/-鼠较C57BL/6鼠炎症感染灶明显增多。流式细胞术结果显示,相对于C57BL/6鼠BANK-/-鼠中枢神经系统中CD8+T细胞百分比明显增多,而脾脏中调节性T细胞百分比明显减少,CD4/CD8比值倒置(P<0.05)。结论:B细胞衔接蛋白BANK的表达抑制EAE炎症反应。

New design for multi-crystal data collection at SSRF

Data collection with microcrystals at synchrotron radiation facilities is challenging because it is difficult to harvest and locate microcrystals. Moreover,microcrystals are sensitive to radiation damage; thus, typically, a complete data set cannot be obtained with a single microcrystal. Herein, we report a new method for data collection with multiple microcrystals having a crystal size ranging from 1 to 30 lm. This method is suitable for not only low-temperature(100 K) data collection but also room-temperature data collection. Thin Kapton membranes were used to capture multiple crystals simultaneously. The microcrystals were visible under an optical microscope and easily located because the membrane was transparent and sufficiently thin. The film was fixed to a bracket that was prepared using a three-dimensional printer. The bracket was fixed on a magnetic base via screwing and employed by the goniometer system for data collection. Multiple data sets of fatty acid-binding protein 4(FABP4) and lysozyme microcrystals were collected using this novel designed device. Finally, the structures of protein FABP4 and lysozyme were obtained from these data via the molecule replacement method. The data statistics reveal that this method provides a comparable result to traditional methods such as a nylon loop.

Potential Applications of Milk Fractions and Valorization of Dairy By-Products: A Review of the State-of-the-Art Available Data, Outlining the Innovation Potential from a Bigger Data Standpoint

The unique composition of milk makes this basic foodstuff into an exceptional raw material for the production of new ingredients with desired properties and diverse applications in the food industry. The fractionation of milk is the key in the development of those ingredients and products;hence continuous research and development on this field, especially various levels of fractionation and separation by filtration, have been carried out. This review focuses on the production of milk fractions as well as their particular properties, applications and processes that increase their exploitation. Whey proteins and caseins from the protein fraction are excellent emulsifiers and protein supplements. Besides, they can be chemically or enzymatically modified to obtain bioactive peptides with numerous functional and nutritional properties. In this context, valorization techniques of cheese-whey proteins, by-product of dairy industry that constitutes both economic and environmental problems, are being developed. Phospholipids from the milk fat fraction are powerful emulsifiers and also have exclusive nutraceutical properties. In addition, enzyme modification of milk phospholipids makes it possible to tailor emulsifiers with particular properties. However, several aspects remain to be overcome;those refer to a deeper understanding of the healthy, functional and nutritional properties of these new ingredients that might be barriers for its use and acceptability. Additionally, in this review, alternative applications of milk constituents in the non-food area such as in the manufacture of plastic materials and textile fibers are also introduced. The unmet needs, the cross-fertilization in between various protein domains,the carbon footprint requirements, the environmental necessities, the health and wellness new demand, etc., are dominant factors in the search for innovation approaches;these factors are also outlining the further innovation potential deriving from those “apparent” constrains obliging science and technology to take them into account.

The Efficiency Evaluation of Commercial Banks Based on DEA/TOPSIS

This paper brings forward an efficiency evaluation method based on DEA/FOPSIS for commercial banks. To avoid the slack of output index, the difference is taken into account in the weight of different output index, mending the shortage of traditional DEA evaluation methods.

Paving the High-Way to Sustainable, Value Adding Open-Innovation Integrating Bigger-Data Challenges: Three Examples from Bio-Ingredients to Robust Durable Applications of Electrochemical Impacts

A trilogy review, based on more than 300 references, is used to underline three challenges facing 1) the supply of sustainable, durable and protected biosourced ingredients such as lipids, 2) the accounting for valuable bio-by-products, such as whey proteins that have added-value potential removing their environmental weight and 3) the practical reliable synthetic biology and evolutionary engineering that already serve as a technology and science basis to expand from, such as for biopolymer growth. Bioresources, which are the major topic of this review, must provide answers to several major challenges related to health, food, energy or chemistry of tomorrow. They offer a wide range of ingredients which are available in trees, plants, grasses, vegetables, algae, milk, food wastes, animal manures and other organic wastes. Researches in this domain must be oriented towards a bio-sustainable-economy based on new valuations of the potential of those renewable biological resources. This will aim at the substitution of fossil raw materials with renewable raw materials to ensure the sustainability of industrial processes by providing bioproducts through innovative processes using for instance micro-organisms and enzymes (the so-called white biotechnology). The final stage objective is to manufacture high value-added products gifted with the right set of physical, chemical and biological properties leading to particularly innovative applications. In this review, three examples are considered in a green context open innovation and bigger data environment. Two of them (lipids antioxidants and milk proteins) concern food industry while the third (biomonomers and corresponding bioplastics and derivatives) relates to biomaterials industry. Lipids play a crucial role in the food industry, but they are chemically unstable and very sensitive to atmospheric oxidation which leads to the formation of numerous by-compounds which have adverse effects on lipids quality attributes and on the nutritive value of meat. To overcome this problem, natural antioxidants, with a positive impact on the safety and acceptability of the food system, have been discovered and evaluated. In the same context, milk proteins and their derivatives are of great interest. They can be modified by enzymatic means leading to the formation of by-products that are able to increase their functionality and possible applications. They can also produce bioactive peptides, a field with almost unlimited research potential. On the other hand, biosourced chemicals and materials, mainly biomonomers and biopolymers, are already produced today. Metabolic engineering tools and strategies to engineer synthetic enzyme pathways are developed to manufacture, from renewable feedstocks, with high yields, a number of monomer building-block chemicals that can be used to produce replacements to many conventional plastic materials. Through those three examples this review aims to highlight recent and important advancements in production, modification and applications of the studied bioproducts. Bigger data analysis and artificial intelligence may help reweight practical and theoretical observations and concepts in these fields;helping to cross the boarders of expert traditional exploration fields and sometime fortresses.

Frontier Analysis of Nepalese Commercial Banks： DEA Approach

The efficiency of any organizations at manufacturing sector or service sector, profit making or non-profit making, is most important factor for survival and growth of the organization. The Data Envelopment Analysis （DEA） technique is one of the most popular and effective tool to measure relative efficiency hence is appropriate to make comparison among similar organizations with multiple output and input. This study performs frontier analysis and measures the relative efficiency of Nepalese commercial banks using DEA approach with two output and two input variables.