A neural network based dynamic forecasting model for Trend Impact Analysis

Trend Impact Analysis is a simple forecasting approach, yet powerful, within the Futures Studies paradigm. It utilizes experts' judgements to explicitly deal with unprecedented future events with varying degrees of severity in generating different possibilities (scenarios) of how the future might unfold. This is achieved by modifying a surprise-free forecast according to events' occurrences based on a Monte-Carlo simulation process. Yet, the current forecasting mechanism of TIA is static. This paper introduces a new approach for constructing TIA by using a dynamic forecasting model based on neural networks. This new approach is designed to enhance the TIA prediction process. It is expected that such a dynamic mechanism will produce more robust and reliable forecasts. Its idea is novel, beyond state of the art and its implementation is the main contribution of this paper.     

Farsightedly stable networks

A set of networks G is pairwise farsightedly stable (i) if all possible farsighted pairwise deviations from any network g G to a network outside G are deterred by the threat of ending worse off or equally well off, (ii) if there exists a farsighted improving path from any network outside the set leading to some network in the set, and (iii) if there is no proper subset of G satisfying conditions (i) and (ii). A non-empty pairwise farsightedly stable set always exists. We provide a full characterization of unique pairwise farsightedly stable sets of networks. Contrary to other pairwise concepts, pairwise farsighted stability yields a Pareto dominant network, if it exists, as the unique outcome. Finally, we study the relationship between pairwise farsighted stability and other concepts such as the largest pairwise consistent set and the von Neumann–Morgenstern pairwise farsightedly stable set.     

Comparison of customer response models

Segmentation of customers by likelihood of repeating business is a very important tool in marketing management. A number of approaches have been developed to support this activity. This article reviews basic recency, frequency, and monetary (RFM) methods on a set of data involving the sale of beef products. Variants of RFM are demonstrated. Classical data mining techniques of logistic regression, decision trees, and neural networks are also demonstrated. Results indicate a spectrum of tradeoffs. RFM methods are simpler, but less accurate. Considerations of balancing cell sizes as well as compressing data are examined. Both balancing expected cell densities as well as compressing RFM variables into a value function were found to provide more accurate models. Data mining algorithms were all found to provide a noticeable increase in predictive accuracy. Relative tradeoffs among these data mining algorithms in the context of customer segmentation are discussed.     

As time goes by: Examining the paradox of stability and change in business networks

Stability and change may seem contradictory features but in business networks, they coexist [Hakansson H, Snehota, I. Developing Relationships in Business Networks. London, Routledge; 1995]. This article explores the paradox of the coexistence of stability and change in an Australian context. Previous research illustrated that stability over time can exist in specific business relationships [Sutton-Brady C, Donnan, M. Nexus nonsense or is it? Conference Proceedings, 19th Annual IMP Conference, Lugano, Switzerland September 2003; 2003]. This research study further investigates time as a proxy variable of stability [Halinen A, Tornroos, J-A. The meaning of time in the study of industrial buyer–seller relationships. In: Moller K, Wilson DT, editors. Business Marketing: An Interaction Approach. Norwell, Mass: Kluwer Academic Publishers; 1995.] and attempts to uncover other variables, which may influence the stability of the relationship. Given the exploratory nature of the research a case study approach was utilized to gain an in-depth understanding of the variables, which may contribute to the stability. This article further advances the concept of time as a proxy variable for stability while investigating what other variables may be crucial in understanding this concept. From analysis of the case studies, the findings show that other variables do play a role in determining the stability and change in the relationships and networks, these included location, product/service quality, technology, cooperativeness, adaptations and cost. The major contribution of this article is the reopening of discussions on time as a proxy variable for stability and attempts to broaden this to include other variables.     

企业家社会网络对企业绩效的影响机制

本文在国内外文献就企业家的社会网络关系研究进行回顾与综述的基础上,总结了社会网络的类型及其正反两方面的影响,指出了当前许多研究片面强调企业家外部网络的作用,而忽视了内部网络。国内外研究表明,企业家社会网络对企业绩效有着正向的影响,其影响机制存在多种变量。本文根据这些研究结果,在理论上提出了企业家内、外社会网络对企业绩效影响机制的模型,并指出了其实践意义以及未来研究方向。     

家庭融资中的有效社会网络:朋友圈还是宗族？

基于2010年中国家庭动态跟踪调查数据(CFPS),本文分析了朋友圈网络和宗族网络对于不同家庭借贷行为的异质效应。在考虑社会网络内生性问题的基础上,研究结果表明:社会网络对家庭融资具有正向作用,在正规渠道中起主导作用的是朋友圈网络,但只影响获得借贷的可能性,而不影响具体的借贷额度;非正规渠道借贷中起主导作用的是宗族网络,同时影响获得借贷的可能性和借贷额度。对于宗族网络而言,强度效应比规模效应更重要,即拥有以祠堂和家谱为宗族联系纽带的家庭更容易获得贷款,而以亲戚拜年人数测度的网络规模没有显著影响;相比“祠堂”载体,“家谱”载体所代表的宗族联系比较松散,但是覆盖范围更广,其对非正规借贷的影响更为稳健。     

基于神经网络的人民币实际有效汇率分析与预测

通过计算人民币实际有效汇率指数,并利用自适应神经网络技术对其未来走势进行预测,结果表明:1994年以来,人民币实际有效汇率指数一直呈稳步上升状态,在近期内仍将维持小幅上升的态势。因此,国际社会要求人民币大幅升值的实际基础是不存在的,“人民币升值论”实质是国际经济持续低迷引起的国外政府与媒体的升值预期。因此,政府应当积极采取有效措施,缓解人民币升值压力,将其对国民经济的危害降低到最小程度。     

Investigating the accuracy of cross-learning time series forecasting methods

The M4 competition identified innovative forecasting methods, advancing the theory and practice of forecasting. One of the most promising innovations of M4 was the utilization of cross-learning approaches that allow models to learn from multiple series how to accurately predict individual ones. In this paper, we investigate the potential of cross-learning by developing various neural network models that adopt such an approach, and we compare their accuracy to that of traditional models that are trained in a series-by-series fashion. Our empirical evaluation, which is based on the M4 monthly data, confirms that cross-learning is a promising alternative to traditional forecasting, at least when appropriate strategies for extracting information from large, diverse time series data sets are considered. Ways of combining traditional with cross-learning methods are also examined in order to initiate further research in the field.     

Emerging patterns of complex technological innovation

Technological innovation is increasingly concerned with complex products and processes. The trend toward greater complexity is suggested by the fact that in 1970 complex technologies comprised 43% of the 30 most valuable world goods exports, but by 1996 complex technologies represented 84% of those goods. These technologies are innovated by self-organizing networks. Networks are those linked organizations that create, acquire, and integrate the diverse knowledge and skills required to innovate complex technologies. Accessing tacit knowledge (i.e., experienced-based, unwritten know-how) and integrating it with codified knowledge is a particular strength of many networks. Self-organization refers to the capacity networks have for reordering themselves into more complex structures (e.g., replacing individual managers with management teams), and for using more complex processes (e.g., evolving strategies) without centralized, detailed managerial guidance. Case studies of the innovation pathways traced by six complex technologies indicate that innovations can be grouped into three quite distinct patterns. Transformation: the launching of a new trajectory by a new coevolving network and technology. Normal: the coevolution of an established network and technology along an established trajectory. Transition: the coevolutionary movement to a new trajectory by an established network and technology. Policy makers and managers face the greatest challenge during those periods of movement from one innovation trajectory to another. These are periods of turbulence; they are the embodiment of Schumpeter's “gales of creative destruction.” This paper investigates how, in six case studies, core capabilities, complementary assets, organizational learning, path dependencies, and the selection environment varied among the innovation patterns. The paper builds on work reported in a recent book by the authors entitled: The Complexity Challenge: Technological Innovation for the 21st Century, Pinter, London, 1999.     

机械结构损伤识别技术的研究

结构的破损、诊断、评估和加固是机械工程中十分重要的一个研究领域，通过对损伤识别技术现状的归纳和总结，介绍了基于模态模型的解析法和基于神经网络技术的非线性映射损伤识别法，并对其发展前景进行了探讨，这对人们了解和研究结构损伤检测具有借鉴作用。