臺灣博碩士論文加值系統

近年來由於國際貿易日益興盛，且全球經濟越來越趨向於共體存亡的趨勢，因此，各國經濟很容易因為全球性之議題而產生巨大的波動，進而延伸出全球性的金融危機，如1997年的亞洲金融風暴、2008年的雷曼兄弟事件，甚至是2011年的歐債危機都說明了上述的狀況。在這種情形之下，無論是政府或企業，都會為了維持整體金融架構的穩定性，而付出許多心血。因此，許多研究開始致力於開發一個精準且穩定的預測模型，來預測詭譎而多變的金融市場
關於公司財務窘境預測，一直以來都是備受關注的研究領域，也有許多模型被推廣出來用以進行預測，如傳統統計中的區別分析、邏輯回歸還有是人工智慧的許多模型。其中又以支援向量機(Support Vector Machine, SVM)為目前學者常使用的機器學習模型，過往的許多研究中也都已經指出SVM的確是一個優秀且穩定的機器學習方法，因此本論文也將以SVM為基礎去建置出公司財務窘境預測模型。
本論文提出一個改良式的離散人工蜂群演算法(Discrete the food source in Artificial Bee Colony, DfABC)來優化SVM核心參數，藉此去提升預測模型之整體成效與穩定性，並透過UCI資料庫中的多個資料集與標準普爾的美國公司信評資料集，來驗證本論文所提出之混和模型擁有較穩定之預測成效與較快的收斂速度。最後實驗也證明本研究所提出來的模型，在於分類準確度與收斂速度兩部分，皆優於本研究相比較之其他人工智慧模型。

In recent years, international trade has been more and more flourishing, and economies around the world depend heavily on one another. Therefore the economics of most countries will fluctuate with global trends, which may even bring out global financial crises, such as the Asian financial turmoil in 1997, the Lehman Brothers incident in America in 2008, and the European debt crisis, which broke out two years ago. Under these circumstances, the countries and companies will have to make a lot of efforts to keep the financial framework stable. Therefore, many researchers have try to develop a stable model to predict the ever-changing financial market accurately.
Research on financial distress always attracts many scholars’ attention, and many research models have been proposed in the last 40 years. From the traditional statistical models, such as the discriminant analysis and logistic regression, to the artificial intelligence models, many researchers have developed different models using one of these methods. In recent years Support Vector Machine (SVM) has become more and more popular, and the predicting models constructed with SVM have better performance than other models do. Based on this reason, we used SVM to construct our predicting model.
In this paper, we proposed an Discrete the food source in Artificial Bee Colony (DfABC) to optimize the SVM kernel parameters, and to improve the classification performance and the stability of the model. Then we used many datasets collected from UC Irvine Machine Learning Repository (UCI) and the Compustat credit rating database in America, to verify that the model we proposed is more stable and accurate than other models we compared. Finally, the experimental results show that, the model we proposed has the best classification accuracy and the best convergence rate compared with any other artificial intelligence models we reviewed

目錄
摘要 i
ABSTRACT ii
誌謝 iv
目錄 v
圖目錄 vii
表目錄 viii
第一章 緒論 1
1.1 研究背景 1
1.2 研究目的 2
1.3 研究限制 3
1.4 研究架構 3
第二章 文獻探討 5
2.1 財務窘境 5
2.2 仿生運算 8
2.3機器學習方法 12
第三章 研究方法 15
3.1人工蜂群演算法 15
3.2改進方法 19
3.3支援向量機參數優化過程 27
3.4實驗流程介紹 29
第四章 財務相關資料集實驗結果 34
4.1財務相關資料集資料介紹 34
4.2 財務相關資料集實驗結果 35
4.3 財務窘境預測指標討論 40
第五章 一般類型資料集實驗結果 42
5.1 一般類型資料集之介紹與實驗結果 42
5.2 DfABC演算法之討論 48
第六章 結論 53
6.1結論與貢獻 53
6.2未來展望 54
參考文獻 55

[1]Akay B., Karaboga D., 2012, "A modified Artificial Bee Colony algorithm for real-parameter optimization", Information Sciences 192, p.120－p.142
[2]Altman E.I., 1968, "Financial ratios discriminant analysis and the prediction of corporate bankruptcy", Journal of Finance 23, p.589－p.609
[3]Bae J.K., 2012, "Predicting financial distress of the South Korean manufacturing industries", Expert Systems with Applications 39, p.9159－p.9165
[4]Blasi L., Barbato S. and Mattei M., 2013, "A particle swarm approach for flight path optimization in a constrained environment", Aerospace Science and Technology 26, p.128-p.137
[5]Boritz J.E., Kennedy D. B., 1995, "Effectiveness of neural network types for prediction of business failure", Expert Systems with Applications 9, p.503－p.512
[6]Beaver W., 1966, "Financial ratios as predictors of failure", Empirical Research in Accounting: Selected Studies 5, p.71－p.111
[7]Carlos S.C., 1996, "Self-organizing neural networks for financial diagnosis", Decision Support Systems 17, p.227－p.238
[8]Chaudhuri A., De K., 2011, "Fuzzy Support Vector Machine for bankruptcy prediction", Applied Soft Computing 11, p.2472－p.2486
[9]Chang J.R., Wei L.Y. and Cheng C.H., 2009, "A hybrid ANFIS model based on AR and volatility for TAIEX forecasting", Applied Soft Computing 11, p.1388－p.1395
[10]Chen H.Y., Leou J.J., 2012, "Saliency-directed color image interpolation using artificial neural network and particle swarm optimization", Journal of Visual Communication and Image Representation 23, p.343-p.358
[11]Chen M.Y., 2013, "A hybrid ANFIS model for business failure prediction utilizing particle swarm optimization and subtractive clustering", Information Sciences 220, p.180－p.195
[12]Chen W.C., Hsu Y.Y., Hsieh L.F. and Tai P.H., 2010, "A systematic optimization approach for assembly sequence planning using Taguchi method, DOE, and BPNN", Expert Systems With Applications 37 p716－726
[13]Cortes C., Vapnik V., 1995, "Support-vector networks", Machine Learning 20, p.273－p.297
[14]Cuevas E., Zaldívar D., Pérez-Cisneros M., Sossa H. and Osuna V., 2013., "Block matching algorithm for motion estimation based on Artificial Bee Colony (ABC)", Applied Soft Computing 13, p.3047－p.3059
[15]Dorigo M., 1992, Optimization, Learning and Natural Algorithms, PhD thesis, Politecnico di Milano, Italy
[16]Dorigo M., Di Caro G. and Gambardella L.M., 1999, "Ant Algorithms for Discrete Optimization", Artificial Life 5, p.137－p.172
[17]Etheridge H.L., Sriram R.S., 1997, "A comparison of the relative costs of financial distress models: Artificial neural networks, logit and multivariate discriminant analysis", Intelligent Systems in Accounting, Finance and Management 6, p.235－p.248
[18]Fletcher D., Goss E., 1993, "Forecasting with neural networks: An application using bankruptcy data", Information and Management 24, p.159－p.167
[19]Frydman H., Altman E.I. and Kao D., 1985, "Introducing recursive partitioning for financial classification: The case of financial distress", Journal of Finance 1, p.269－p.291
[20]Fitzpartrick P.J., 1932, "A comparison of ratios of successful industrial enterprises with those of failed companies", Journal of Accounting Research 10, p.598－p.605
[21]Gao L., Huang J. and Li X., 2012, "An effective cellular particle swarm optimization for parameters optimization of a multi-pass milling process", Applied Soft Computing 12, p.3490－p.3499
[22]Hsieh T.J., Hsiao H.F. and Yeh W.C., 2011, "Forecasting stock markets using wavelet transforms and recurrent neural networks: An integrated system based on artificial bee colony algorithm", Applied Soft Computing 11, p.2510－p.2525
[23]Hsieh T.J., Hsiao H.F. and Yeh W.C., 2012, "Mining financial distress trend data using penalty guided support vector machines based on hybrid of particle swarm optimization and artificial bee colony algorithm", Neuro computing 82, p.196－p.206
[24]Kaiser H.F., 1960, “The application of electronic computers to factor analysis”, Educational and Psychological Measurement 20, .p.141－p.151.
[25]Karaboga D., Basturk B., 2007, "A powerful and efficient algorithm for numerical function optimization: artificial bee colony (ABC) algorithm", Journal of Global Optimization 39, p.459－p.471
[26]Kashan M.H, Nahavandi N, and Kashan A.H., 2012, "DisABC: A new artificial bee colony algorithm for binary optimization", Applied Soft Computing 12, p.342－p.352
[27]Kennedy J., Eberhart R., 1995, "Particle Swarm Optimization", Proceedings of IEEE International Conference on Neural Networks 4, p.1942－p.1948
[28]Kim M.J, Han I., 2003, "The discovery of experts’ decision rules from qualitative bankruptcy data using genetic algorithms", Expert Systems with Applications 25, p.637－p.646
[29]Kıran M.S., Gündüz M., 2013, "A recombination-based hybridization of particle swarm optimization and artificial bee colony algorithm for continuous optimization problems", Applied Soft Computing 13, p.2188-p.2203
[30]Ko P.C., Lin P.C., 2006, "An evolution-based approach with modularized evaluations to forecast financial distress", Knowledge-Based Systems 19, p.84–p.91
[31]Li H., Sun J., 2008, "Ranking-order case-based reasoning for financial distress prediction", Knowledge-Based Systems 21, p.868－p.878
[32]Li G., Niu P. and Xiao X., 2012, "Development and investigation of efficient artificial bee colony algorithm for numerical function optimization", Applied Soft Computing 12, p.320－p.332
[33]Marinaki M., Marinakis Y. and Zopounidis C., 2010, "Honey Bees Mating Optimization algorithm for financial classification problems", Applied Soft Computing 10, p.806–p.812
[34]Marinakis Y., Marinakis M., Doumpos M. and Zopounidis C.,2009, "Ant colony and particle swarm optimization for financial classification problems", Expert Systems with Applications 36, p.10604－p.10611
[35]Navalertporn T., Afzulpurkar N.V., 2011, "Optimization of tile manufacturing process using particle swarm optimization", Swarm and Evolutionary Computation 1, p.97－p.109
[36]Ohlson J.A., 1980 , "Financial ratios and probabilistic prediction of bankruptcy", Journal of Accounting Research 18, p.109－p.131
[37]Odom M., Sharda R., 1990, "A neural networks model for bankruptcy prediction", In Proceedings of the IEEE international conference on neural network 2, p.163－p.168
[38]Porta Garcia M.A., Montiel O., Castillo O., Sepu´lveda R. and Melin P., 2009, "Path planning for autonomous mobile robot navigation with ant colony optimization and fuzzy cost function evaluation", Applied Soft Computing 9, p.1102－p.1110
[39]Rajabioun R., 2011, "Cuckoo Optimization Algorithm", Applied Soft Computing 11, p.5508－p.5518
[40]Rodriguez F.J., Lozano M., García-Martínez C. and González-Barrera J.D., 2013, "An artificial bee colony algorithm for the maximally diverse grouping problem", Information Sciences 230, p.183－p.196
[41]Shaco N.C, Ganguly S and Das D, 2012, "Multi-objective planning of electrical distribution systems incorporating sectionalizing switches and tie-lines using particle swarm optimization", Swarm and Evolutionary Computation 3, p.15－p.32
[42]Seckiner S.U., Kurt M., 2008, "Ant colony optimization for the job rotation scheduling problem", Applied Mathematics and Computation 201, p.149-p.160
[43]Shin K.S., Lee Y.J., 2002, "A genetic algorithm application in bankruptcy prediction modeling", Expert Systems with Applications 23, p.321－p.328
[44]Sue J., Li H., 2011, "Dynamic financial distress prediction using instance selection for the disposal of concept drift", Expert Systems with Applications 38, p.2566－p.2576
[45]Sue J., Li H., 2012, "Financial distress prediction using support vector machines: Ensemble vs. individual", Applied Soft Computing 12, p.2254－p.2265
[46]Sue J., Li H. and Zhang M., 2009, "Multiple Classifiers Hybrid Combination For Companies’Financial Distress Prediction", Systems Engineering － Theory & Practice 29, p.78－p.86
[47]Taher S.A., a Bagherpour R., 2013, "A new approach for optimal capacitor placement and sizing in unbalanced distorted distribution systems using hybrid honey bee colony algorithm", Electrical Power and Energy Systems 49, p.430-p.448
[48]Taheri J., Lee Y.C., . Zomaya A.Y. and Siegel H.J., 2013, "A Bee Colony based optimization approach for simultaneous job scheduling and data replication in grid environments", Computers & Operations Research 40, p.1564－p.1578
[49]Tavares Neto R.F., Godinho Filho M., 2011, "An ant colony optimization approach to a per mutational flow shop scheduling problem with outsourcing allowed", Computers & Operations Research 38, p.1286－p.1293
[50]Wang Z., Li H., 2007, "Financial distress prediction of Chinese listed companies: a rough set methodology", Chinese Management Studies 1, p.93－p.110
[51]Xu C., Duan H., 2010, "Artificial bee colony (ABC) optimized edge potential function (EPF) approach to target recognition for low-altitude aircraft", Pattern Recognition Letters 31, p.1759－p.1772
[52]Xu C., Duan H. and Liu F., 2010, "Chaotic artificial bee colony approach to Uninhabited Combat Air Vehicle (UCAV) path planning", Aerospace Science and Technology 14, p.535－p.541
[53]Yang J., Zhuang Y., 2010, "An improved ant colony optimization algorithm for solving a complex combinatorial optimization problem", Applied Soft Computing 10, p.653－p.660
[54]Zhang Y, Gong D.W. and Ding Z, 2012, "A bare-bones multi-objective particle swarm optimization algorithm for environmental/economic dispatch", Information Sciences 192, p.213－p.227