A fuzzy neural network combined with technical indicators and its application to Baltic Dry Index forecasting

To enhance the technical analysis prediction of freight rate trend in the dry bulk shipping market, a fuzzy neural network combined with technical indicators is developed. Firstly, five technical indicators often used in the financial market including %R, RSI, MACD, CCI, and MA are chosen as input signals, and the accuracy rate for forecasting Baltic Dry Index (BDI) trend is about 62%. Secondly, a traditional fuzzy neural network is applied to the forecasting of BDI. The RMSPE of forecasting BDI by the traditional fuzzy neural network is 24.76. Finally, the integrated fuzzy neural network combined with technical indicators is applied to forecasting BDI. The accuracy rate for forecasting BDI trend is 83%, and the RMSPE of forecasting BDI is 1.89. The results show that the integrated fuzzy neural network combined with technical indicators has a higher forecasting accuracy rate than the technical indicator approach or the fuzzy neural network approach.

Language

  • English

Media Info

Subject/Index Terms

Filing Info

  • Accession Number: 01709337
  • Record Type: Publication
  • Files: TRIS
  • Created Date: Apr 30 2019 3:00PM