Fuzzy Local Trend Transform based Fuzzy Time Series Forecasting Model

A fuzzy local trend transform based fuzzy time series forecasting model is proposed to improve practicability and forecast accuracy by providing forecast of local trend variation based on the linguistic representation of ratios between any two consecutive points in original time series. Local trend variation satisfies a wide range of real applications for the forecast, the practicability is thereby improved. Specific values based on the forecasted local trend variations that reflect fluctuations in historical data are calculated accordingly to enhance the forecast accuracy. Compared with conventional models, the proposed model is validated by about 50% and 60% average improvement in terms of MLTE (mean local trend error) and RMSE (root mean squared error), respectively, for three typical forecasting applications. The MLTE results indicate that the proposed model outperforms conventional models significantly in reflecting fluctuations in historical data, and the improved RMSE results confirm an inherent enhancement of reflection of fluctuations in historical data and hence a better forecast accuracy. The potential applications of the proposed fuzzy local trend transform include time series clustering, classification, and indexing.

[1]  B. Chissom,et al.  Forecasting enrollments with fuzzy time series—part II , 1993 .

[2]  Jingpei Dan,et al.  Mean Local Trend Error and Fuzzy-Inference-Based Multicriteria Evaluation for Supply Chain Demand Forecasting , 2011, J. Adv. Comput. Intell. Intell. Informatics.

[3]  Lotfi A. Zadeh,et al.  The concept of a linguistic variable and its application to approximate reasoning-III , 1975, Inf. Sci..

[4]  Tzung-Pei Hong,et al.  Mining fuzzy frequent trends from time series , 2009, Expert Syst. Appl..

[5]  B. Chissom,et al.  Fuzzy time series and its models , 1993 .

[6]  Kunhuang Huarng,et al.  Heuristic models of fuzzy time series for forecasting , 2001, Fuzzy Sets Syst..

[7]  J. Bezdek,et al.  FCM: The fuzzy c-means clustering algorithm , 1984 .

[8]  Jin Hee Yoon,et al.  Fuzzy time series reflecting the fluctuation of historical data , 2010, 2010 Seventh International Conference on Fuzzy Systems and Knowledge Discovery.

[9]  Hui-Kuang Yu.  A refined fuzzy time-series model for forecasting , 2005 .

[10]  Ching-Hsue Cheng,et al.  Trend-Weighted Fuzzy Time-Series Model for TAIEX Forecasting , 2006, ICONIP.

[11]  Ildar Z. Batyrshin,et al.  Perception-based approach to time series data mining , 2008, Appl. Soft Comput..

[12]  Reda Alhajj,et al.  Discovering all frequent trends in time series , 2004 .

[13]  Lotfi A. Zadeh,et al.  The Concepts of a Linguistic Variable and its Application to Approximate Reasoning , 1975 .

[14]  Shyi-Ming Chen,et al.  Handling forecasting problems using fuzzy time series , 1998, Fuzzy Sets Syst..

[15]  Tiffany Hui-Kuang Yu,et al.  Ratio-based lengths of intervals to improve fuzzy time series forecasting , 2006, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).

[16]  Shyi-Ming Chen,et al.  Forecasting enrollments based on fuzzy time series , 1996, Fuzzy Sets Syst..

[17]  Lotfi A. Zadeh,et al.  Outline of a New Approach to the Analysis of Complex Systems and Decision Processes , 1973, IEEE Trans. Syst. Man Cybern..

[18]  Ching-Hsue Cheng,et al.  Multi-attribute fuzzy time series method based on fuzzy clustering , 2008, Expert Syst. Appl..

[19]  Kunhuang Huarng,et al.  Effective lengths of intervals to improve forecasting in fuzzy time series , 2001, Fuzzy Sets Syst..

[20]  Shyi-Ming Chen,et al.  Fuzzy Forecasting Based on Fuzzy-Trend Logical Relationship Groups , 2010, IEEE Transactions on Systems, Man, and Cybernetics, Part B (Cybernetics).