风险条件下研发项目改进DEA选择模型

doi:10.16381/j.cnki.issn1003-207x.2018.07.006

摘要/Abstract

摘要： 研发项目是企业提高竞争力的关键，研发项目选择关系到企业的战略和未来发展趋势。研发项目在生命周期内面临技术风险、突发风险和市场风险，本文考虑到研发项目的风险特征，结合企业战略，构建了基于效率排序的研发项目选择模型。首先，本文对研发项目的有效性和相对于其它备选项目的相对优势进行分析；然后针对数据包络分析模型排序的不足，结合平衡计分卡理念，规范研发项目投入的比例，引入实物期权理论，改进数据包络分析模型，实现了对研发项目的效率排序；最后通过实际算例对模型进行验证、横向对比和敏感性分析，结果表明：相对于标准数据包络分析模型，本文提出的模型具有更高的效率区分度，并且能够敏感地捕捉到研发项目投入和产出的变化对效率影响的演变过程。

关键词: 研发项目, 选择模型, 风险条件, 数据包络分析, 平衡计分卡

Abstract: For many enterprises, Research and Development(R&D) projects play a vital role in improving competitiveness, and the R&D project is the impetus of enterprise survival and development. The R&D project selection is a process of logical analysis and comprehensive judgment on an investment system with complex multi factors, and it is one of the most important and complex problems in the project management field.Meanwhile, R&D project selection is closely related to enterprise strategy development and future trends. Compared with general projects, high innovative R&D projects have greater uncertainty, which are not only reflected by the technical factors of projects themselves, but also by the factors of market changes and unexpected competitors. The high uncertainty of R&D projects brings high risks. It is also the case that R&D projects are affected by market, technology and emergency risks during the life cycle. Market risk is the uncertainty of potential R&D project cash flow, technology risk is the probable loss caused by technology uncertainty, and emergency risk is the impact of unexpected events on R&D project cash flow. The existed risks make R&D project selection more challenging. In general, R&D projects have large investment and long life cycles, which are useful for enterprise competitive advantage and future growth. It will affect enterprise development for several years whether to choose the R&D project suitable for enterprise strategy and whether to response to risks during R&D process. Therefore, it has great theoretical and practical significance to study R&D project selection under risk condition.
In this paper, drawing on the risk characteristics associated with R&D projects and enterprise strategy, the R&D project selection model based on efficiency sorting is constructed and presented.To begin with, the effectiveness of R&D projects and the relative advantages compared to alternative projects are analyzed; Secondly, focus is put on the drawbacks of DEA model, combining with the concept of BSC. According to enterprise strategy, the relative importance of individual R&D project evaluation indicator is different. During the evaluation, it is necessary to introduce weight change information into the DEA method, thus a R&D project selection model is built based on DEA method with guarantee domain. Balanced Score Card (BSC) is a multiple performance evaluation system. It can transform enterprise tasks, decisions and internal departments into a variety of interrelated goals, and then decompose theses targets into multiple indicators. Based on the idea of BSC, the enterprise strategy is introduced into the DEA model, which can allocate the change range of input indicator weights under the same score card. It shows that DEA model is improved by introducing the real option theory and constraining the proportion of R&D project inputs, then the efficiency sorting of R&D projects is realized; Finally, the proposed model in this paper is verified through an actual example, with transverse contrast and sensitivity analysis. The R&D project selection differences between using the proposed DEA model and the standard DEA model in an aerospace enterprise are compared, and the corresponding operation code is developed by MatLab7.0. The results reveal that the model presented in this paper has higher efficiency division compared with the standard DEA model, and it could capture sensitively the evolution process that R&D project input and output changes impact upon efficiency.
Above all,facing enterprise strategy, the selection model of multiple R&D projects in an enterprise is discussed under risk condition. Based on real option theory, constraining DEA model weight assignment with the BSC concept, R&D project investment factors and enterprise strategy are combined.Taking into account risks and uncertainties, the weight changes are limited within a special range, the standard C²R model is improved, and the sort results validity is made. The proposed model has higher discrimination. At the same time, it can capture, with precision and accuracy the process of input and output parameters on efficiency influence. The model proposed in this paper can effectively sort the efficiency of R&D projects, and effectively solve the selection of multiple R&D projects.

Key words: research and development projects, selection model, risk condition, data envelopment analysis, balanced score card

中图分类号:

F830

谷晓燕, 何锋. 风险条件下研发项目改进DEA选择模型[J]. 中国管理科学, 2018, 26(7): 47-54.

GU Xiao-yan, HE Feng. The Improved DEA Model for R&D Project Selection under Risk Condition[J]. Chinese Journal of Management Science, 2018, 26(7): 47-54.

参考文献

[1] Bin A, Azevedo A, Duarte L, et al. R&D and innovation project selection:Can optimization methods be adequate?[J]. Procedia Computer Science, 2015, 55:613-621.

[2] Liesi J, Punkka A. Baseline value specification and sensitivity analysis in multiattribute project portfolio selection[J]. European Journal of Operational Research, 2014, 237(6):946-956.

[3] Huang Xiaoxia, Zhao Tianyi. Project selection and scheduling with uncertain net income and investment cost[J]. Applied Mathematics and Computation, 2014, 247:61-71.

[4] 谷晓燕.基于实物期权的研发项目动态投资决策模型[J].中国管理科学,2015,23(7):94-102.

[5] Roland J, Figueira J R, Smet Y D. Finding compromise solutions in project portfolio selection with multiple experts by inverse optimization[J]. Computers & Operations Research, 2016, 66:12-19.

[6] Hassanzadeh F, Nemati H, Sun Minghe.Robust optimization for interactive multiobjective programming with imprecise information applied to R&D project portfolio selection[J] European Journal of Operational Research, 2014, 238(1):41-53.

[7] 王景玫,郭鹏,赵静.R&D项目组合鲁棒性风险测度及选择模型研究[J].运筹与管理,2017,26(6):140-148.

[8] Bhattacharyya R. A grey theory based multiple attribute approach for R&D project portfolio selection[J].Fuzzy Information and Engineering, 2015, 7(2):211-225.

[9] Fliedner T, Liesiö J.Adjustable robustness for multi-attribute project portfolio selection[J]. European Journal of Operational Research, 2016, 252(3):931-946.

[10] Hassanzadeh F, Modarres M, Nemati H R, et al. A robust R&Dproject portfolio optimization model for pharmaceutical contract research organizations[J]. International Journal of Production Economics, 2014, 158:18-27.

[11] Shakhsi-Niaei M, Torabi S A, Iranmanesh S H.A comprehensive framework for project selection problem under uncertainty and real-world constraints[J]. Computers &Industrial Engineering, 2011, 61(1):226-237.

[12] Costantino F, Gravio G D, Nonino F.Project selection in project portfolio management:An artificial neural network model based on critical success factors[J].International Journal of Project Management,2015,33(8):1744-1754.

[13] Abbassi M, Ashrafi M, Tashnizi E S.Selecting balanced portfolios of R&D projects with interdependencies:A Cross-Entropy based methodology[J]. Technovation, 2014, 34(1):54-63.

[14] Dutra C C, Ribeiro J L D, de Carvalho M M. An economic-probabilistic model for project selection and prioritization[J].International Journal of Project Management, 2014, 32(6):1042-1055.

[15] Chang PT, Lee JH. A fuzzy DEA and knapsack formulation integrated model for project selection[J]. Computers & Operations Research, 2012, 39(1):112-25.

[16] Umut R. Tuzkaya, Ezgi Yolver. R&D project selection by integrated grey analytic network process and grey relational analysis:An implementation for home appliances company[J]. Journal of Aeronautics and Space Technologies, 2015, 8(2):35-41.

[17] Tofighian A A, Naderi B. Modeling and solving the project selection and scheduling[J]. Computers & Industrial Engineering, 2015, 83:30-38.

[18] Karasakal E, Aker P.A multicriteria sorting approach based on data envelopment analysis for R&D project selection problem[J].The International Journal of Management Science,2016,12(6):1-14.

[19] 李琳,黄海军,汪寿阳.基于DEA/AR博弈交叉效率方法的学术期刊评价研究[J]. 管理科学学报,2016,19(04):118-126.

[20] Wu Jie,Chu Junfei,Zhu Qingyuan,et al.DEA cross-efficiency evaluation based on statisfaction degree:An application to technology selection[J]. International Journal of Production Research, 2016, 54(20):5990-6007.

[21] Liu JS, Lu LYY, Lu Wenmin. Research fronts in data envelopment analysis[J]. Omega, 2016, 58:33-45.

[22] Charnes A,Cooper W W,Rhodes E.Measuring the efficiency of decision making units[J].European Journal of Operational Research,1978,2(6):429-444.

[23] 张秀峰,陈光华,杨国梁.基于DEA模型的产学研合作研发效率研究——以不同所有制企业主导的产学研合作研发项目为例[J].研究与发展管理,2016,(05):82-90.

[24] 陈光宇,菊芳,王瑞琦,苏枭凌.基于系统动力学与DEA的企业技术创新项目效率评价方法研究[J].工业技术经济,2016,(4):43-52.

[25] 谷晓燕,何锋,蔡晨.风险条件下基于实物期权的研发项目多阶段评价模型[J].中国管理科学,2011,19(4):68-75.

[26] Ross S A. Return, risk, and arbitrage[M]//Friend I, Bicksler J. Risk and return in finance.Ballinger,MA:Cambridge,1976:189-218.

[27] 陶杰,卢超.整数DEA问题的求解方法与改进[J].中国管理学,2017,25(6):151-160.