Forecasting of Net Asset Value using Modified Whale Optimization Algorithm Based Ensemble Model
Sarbeswara Hota1, Pranati Satapathy2, Debahuti Mishra3
1Sarbeswara Hota, Department of Computer Science & Engineering, Siksha O Anusandhan Deemed to Be University, Bhubaneswar (Odisha), India.
2PranatiSatapathy, MCA, Department of Integrated, Utkal University, Bhubaneswar (Odisha), India.
3Debahuti Mishra, Department of Computer Science & Engineering, Siksha O Anusandhan Deemed to Be University, Bhubaneswar (Odisha), India.
Manuscript received on 07 March 2019 | Revised Manuscript received on 20 March 2019 | Manuscript published on 30 March 2019 | PP: 379-384 | Volume-8 Issue-5, March 2019 | Retrieval Number: E3168038519/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: Net Asset value (NAV) prediction is considered as a financial time series forecasting problem. Different linear and nonlinear time series forecasting models have been used in NAV prediction by various researchers. In this work, an ensemble model is proposed combining AMA as linear model and ANN and FLANN models as nonlinear models for forecasting of NAV data of TATA Dividend Yield Fund-Direct Growth and SBI Magnum Equity mutual funds. The individual models are trained with conventional LMS algorithm. It is a weighted linear ensemble model where the weights are optimized using a modified Whale Optimization Algorithm. The empiricalforecasting performance of the modified Whale Optimization Algorithm based ensemble model along with GA and PSO based ensemble models and the individual models are analyzed. The results demonstrate that the proposed ensemble model outperforms the other models.
Keyword: Functional Link Artificial Neural Network, Least Mean Square, Net Asset Value, Prediction Performance,Whale Optimization Algorithm.
Scope of the Article: Cross-Layer Optimization