PERFORMANCE COMPARISON OF ARTIFICIAL INTELLIGENCE METHODS FOR PREDICTING CASH FLOW

Cash flow forecasting is indispensable for managers, investors and banks. However, which method is more robust has been argued under the condition of small size samples. With sliding window technique we create the Response Sur- face, Back Propagation Neural Network, Radial Basis Functions Neural Network and Support Vector Machine models respectively, which are examined by compar- ing performances of training and simulation. Performances of training models are measured by mean of squared errors while that of simulation is done by average relative errors of the results. By comparison, Support Vector Machine is most robust to forecast cash flow, followed by Radial Basis Function Neural Network, the third Back Propagation Neural Network and the last Response Surface Model. The optimal result of each model depends on the window size of the transmitter.

[1]  Peter Norvig,et al.  Artificial Intelligence: A Modern Approach , 1995 .

[2]  Preston W. Estep.  Cash Flows, Asset Values, and Investment Returns , 2003 .

[3]  Chia-Shang James Chu,et al.  Time Series Segmentation: A Sliding Window Approach , 1995, Inf. Sci..

[4]  Erhard Rank,et al.  Application of Bayesian trained RBF networks to nonlinear time-series modeling , 2003, Signal Process..

[5]  Carlo Vercellis,et al.  Combining discrete SVM and fixed cardinality warping distances for multivariate time series classification , 2010, Pattern Recognit..

[6]  Tho Lai Mooi.  PREDICTING FUTURE CASH FLOWS: DOES CASH FLOW HAVE INCREMENTAL INFORMATION OVER ACCRUAL EARNINGS? , 2010 .

[7]  Lutgarde M. C. Buydens,et al.  Using support vector machines for time series prediction , 2003 .

[8]  Robert L. K. Tiong,et al.  Model on cash flow forecasting and risk analysis for contracting firms , 2002 .

[9]  Kyoung-jae Kim,et al.  Financial time series forecasting using support vector machines , 2003, Neurocomputing.

[10]  Kate Smith-Miles,et al.  Cash flow forecasting using supervised and unsupervised neural networks , 2000, Proceedings of the IEEE-INNS-ENNS International Joint Conference on Neural Networks. IJCNN 2000. Neural Computing: New Challenges and Perspectives for the New Millennium.

[11]  Antônio de Pádua Braga,et al.  An efficient multi-objective learning algorithm for RBF neural network , 2010, Neurocomputing.

[12]  Mark L. DeFond,et al.  Investor Protection and Analysts' Cash Flow Forecasts Around the World , 2007 .

[13]  Ammar Peter Kaka,et al.  A novel multiple linear regression model for forecasting S-curves , 2006 .

[14]  George M. Siouris,et al.  Applied Optimal Control: Optimization, Estimation, and Control , 1979, IEEE Transactions on Systems, Man, and Cybernetics.

[15]  Weijin Jiang,et al.  Nonlinear time series forecasting of time-delay neural network embedded with Bayesian regularization , 2008, Appl. Math. Comput..

[16]  E. Muniz,et al.  Addition of methacryloil groups to poly(vinyl alcohol) in DMSO catalyzed by TEMED: Optimization through response surface methodology , 2006 .

[17]  Dan Givoly,et al.  The Quality of Analysts' Cash Flow Forecasts , 2008 .

[18]  Fionnuala M. Gormley,et al.  The utility of cash flow forecasts in the management of corporate cash balances , 2007, Eur. J. Oper. Res..

[19]  A. H. Boussabaine,et al.  Modelling cost‐flow forecasting for water pipeline projects using neural networks , 1999 .

[20]  M. Rodrigues,et al.  Response surface analysis and simulation as a tool for bioprocess design and optimization , 2000 .

[21]  Tero Haahtela,et al.  Regression sensitivity analysis for cash flow simulation based real option valuation , 2010 .

[22]  Jianguo Luo,et al.  Nonlinear noise reduction of chaotic time series based on multidimensional recurrent LS-SVM , 2008, Neurocomputing.

[23]  Weimin Ma,et al.  Notice of RetractionCash flow forecasting based on GA-BP model in valuation , 2010, 2010 IEEE International Conference on Advanced Management Science(ICAMS 2010).

[24]  Min-Yuan Cheng,et al.  Evolutionary fuzzy decision model for cash flow prediction using time-dependent support vector machines , 2011 .

[25]  Barbara Pirchegger.  Hedge accounting incentives for cash flow hedges of forecasted transactions , 2006 .

[26]  Juan Julián Merelo Guervós,et al.  Evolving RBF neural networks for time-series forecasting with EvRBF , 2004, Inf. Sci..

[27]  Edward J. Riedl.  Discussion of “Accounting Conservatism and the Temporal Trends in Current Earnings’ Ability to Predict Future Cash Flows versus Future Earnings: Evidence on the Trade‐off between Relevance and Reliability”* , 2010 .

[28]  Anthony C. Atkinson,et al.  Optimum Experimental Designs, with SAS , 2007 .

[29]  M. Sulaiman Khan,et al.  A sliding windows based dual support framework for discovering emerging trends from temporal data , 2010, Knowl. Based Syst..

[30]  Reuven Lehavy.  Discussion of “Are earnings forecasts more accurate when accompanied by cash flow forecasts?” , 2009 .

[31]  Héctor Pomares,et al.  Time series analysis using normalized PG-RBF network with regression weights , 2002, Neurocomputing.

[32]  Jeffrey S. Russell,et al.  Cash Flow Forecasting Model for General Contractors Using Moving Weights of Cost Categories , 2005 .

[33]  Xiangnian Huang,et al.  Human recognition based on head-shoulder moment feature , 2008, 2008 IEEE International Conference on Service Operations and Logistics, and Informatics.

[34]  Zhe George Zhang,et al.  Forecasting stock indices with back propagation neural network , 2011, Expert Syst. Appl..

[35]  Ravi Sankar,et al.  Time Series Prediction Using Support Vector Machines: A Survey , 2009, IEEE Computational Intelligence Magazine.

[36]  Yoonseok Zang,et al.  Do Direct Cash Flow Disclosures Help Predict Future Operating Cash Flows and Earnings , 2009 .

[37]  Min Gan,et al.  A locally linear RBF network-based state-dependent AR model for nonlinear time series modeling , 2010, Inf. Sci..

[38]  Chaoju Hu,et al.  Improved Methods of BP Neural Network Algorithm and its Limitation , 2010, 2010 International Forum on Information Technology and Applications.

[39]  G. Box,et al.  On the Experimental Attainment of Optimum Conditions , 1951 .

[40]  Y. C. Kog,et al.  Neural networks for construction project success , 1997 .

[41]  H. Pomares,et al.  A heuristic method for parameter selection in LS-SVM: Application to time series prediction , 2011 .

[42]  Nikolai Buzikashvili.  Comparing Web Logs: Sensitivity Analysis and Two Types of Cross-Analysis , 2006, AIRS.