Evaluating the Effect of Affinity Card Programs on Customer Profitability Using Propensity Score Matching

Affinity card programs have become popular in recent times and account for one fifth of all credit card accounts. There is no research that links affinity card programs to customer profitability. Moreover, little is known about what type of affinity card programs would lead to higher profit. Using a large proprietary dataset we answer the above questions. We also apply propensity score matching, a relatively new technique, to control for selection bias in addressing the above issues. Contrary to previous research and common belief, we show that affinity card customers are no more profitable than non-affinity card holders. We also show that sports-based affinity programs are the least profitable and surprisingly, alumni-based affinity programs also do poorly relative to other types of affinity. On the positive side, affinity card customers are lower risk and help to lower the average risk of the portfolio of customers.     

Wages, inflation, and mortgage design

By virtue of creating asset-liability mismatch, conventional long-term, fixed-rate mortgage loans inherently introduce excess interest risk to the financial systems. Considering that inflation is in part the reason for this excess interest risk, it seems natural to redesign mortgages in such a way that over time mortgage payments could, at least in part, reflect inflation. In this paper, I show that by allowing payments to adjust to inflation, particularly that of wages, by incorporating a prespecified growth rate into mortgage payments, mortgage loans become more affordable while bank interest spreads become less volatile, making the banking system less unstable.     

Application of ANFIS to exchange rate forecasting

The need of exchange rate forecasting in order to preventing its disruptive movements has engrossed many policy-makers and economists for many years. The determinants of exchange rate have grown manifold making its behavior complex, nonlinear and volatile so that nonlinear models have better performance for its forecasting. In this study the accuracy of ANFIS as the nonlinear model and ARIMA as the linear models for forecasting 2, 4 and 8 days ahead of daily Iran Rial/∈ and Rial/US$ was compared. Using forecast evaluation criteria we found that nonlinear model outperforms linear model in all three horizons.     

On uniform convergence of undiscounted optimal programs in the Mitra–Wan forestry model: The strictly concave case

In this paper, we show that the 1986 Mitra–Wan result establishing asymptotic convergence of maximal programs to the unique golden-rule forest in the case of undiscounted, strictly concave felicity functions can be strengthened, in the same setting, to the  uniform  asymptotic convergence of  optimal  programs to the unique golden-rule forest. We work with a notationally reformulated version of the model that may have independent interest.     

TD-LTE抢占无线全新商机

如今,为了努力满足用户对移动数据日益增长的需求,大部分运营商的网络和频段都在满负荷运行。据相关数据显示,2010年用户每月使用的数据流量已经超过了5GB。由于数据增长的关键驱动因素——smartphone的普及率在全球仍低于20%,运营商预计用户每月使用的数据流量仍将继续增长。因此,如何充分利用自身的频谱资源、开发包括TD-LTE在内的不同技术选择的潜力,就成为运营商极为关注的重要课题。     

A gossip based information fusion protocol for distributed frequent itemset mining

The computational complexity, huge memory space requirement, and time-consuming nature of frequent pattern mining process are the most important motivations for distribution and parallelization of this mining process. On the other hand, the emergence of distributed computational and operational environments, which causes the production and maintenance of data on different distributed data sources, makes the parallelization and distribution of the knowledge discovery process inevitable. In this paper, a gossip based distributed itemset mining (GDIM) algorithm is proposed to extract frequent itemsets, which are special types of frequent patterns, in a wireless sensor network environment. In this algorithm, local frequent itemsets of each sensor are extracted using a bit-wise horizontal approach (LHPM) from the nodes which are clustered using a leach-based protocol. Heads of clusters exploit a gossip based protocol in order to communicate each other to find the patterns which their global support is equal to or more than the specified support threshold. Experimental results show that the proposed algorithm outperforms the best existing gossip based algorithm in term of execution time.     

An examination of the relationship among consumer lifestyles,ethnocentrism, knowledge structures,attitudes and behavioural tendencies: a comparative study in two CIS states

The objective of this study is to investigate ethnocentric and/or regiocentric behaviour of Azeri and Kyrgyz consumers. In particular, the study focuses on how ethnocentrism explains consumers' attitudes, intentions and actual purchasing behaviour towards products from major sourcing countries. Data for the study were collected through personal interviews in four districts of Greater Bishkek: the capital city of Kyrgyz Republic, and Baku, the capital city of Azerbaijan. Survey findings lend greater support to earlier studies conducted in the USA, Western and Eastern Europe and Japan. Non-ethnocentric Kyrgyz and Azeri consumers have significantly more favourable belief structures, attitudes, intentions and the resultant purchasing behaviour regarding imported products compared to their ethnocentric Azeri and Kyrgyz consumer counterparts. The findings of the study offer important research, public policy and managerial implications for companies, government agencies and international donor agencies alike who are either operating in the region or contemplating an entry in the future. Foreign companies may use pan-regional marketing strategies and may be able to standardise their products and marketing strategies in the region, since consumers have identical and/or very similar use behaviour and uses for the products and services.     

Market reaction to the merger announcements of US banks: A non-parametric X-efficiency framework

This paper investigates the short-term market reaction of nine profit-efficiency, pre-classified merger deals of US banks over the time period from 1992 to 2003. The findings show that mergers combining low efficiency acquirers and targets create significant market returns following the merger event, while mergers combining the least efficient acquirers with moderately efficient targets diminish the acquirer's wealth more than any other type of merger. Furthermore, findings show that acquirers generally lose about 2.5% of their wealth upon the merger announcement while targets experience, on average, significant market returns of 15.5% following the merger announcement.The findings of the cross sectional analysis show that the CARs of acquirers are positively related to their technical efficiency and geographic diversification, while targets' CARs are negatively related to both target size and revenue efficiency.