Earnings per share (EPS) represents the profitability of a common stock and the financial performance of a particular company. Therefore, EPS is often regarded as a major indicator for investors to purchase stocks. The traditional approach is to use a conventional linear time series model for EPS prediction. However, the results would be in doubt when the forecasting problems are nonlinear. For this reason, this paper proposes a fusion forecasting model that incorporates an autoregressive model into an adaptive network-based fuzzy inference system (ANFIS) with three facets: (1) test the lag period of EPS; (2) take fuzzy inference systems (FIS) to fuzzify the past periods of EPS based on the AR concept and use adaptive networks to tune optimal parameters; and (3) employ an integrated ANFIS model to predict EPS. To illustrate the proposed model, 15-quarter EPS data are employed. The experimental results indicate that the proposed model outperforms the listing models.
|Number of pages||14|
|Journal||International Journal of Innovative Computing, Information and Control|
|Publication status||Published - 2011 Sep 1|
All Science Journal Classification (ASJC) codes
- Theoretical Computer Science
- Information Systems
- Computational Theory and Mathematics