Fuzzy Logic-Based Japanese Candlestick Pattern Recognition and Financial Forecast


This paper discusses fuzzy-logic based Japanese candlestick pattern recognition and financial forecasting. Fuzzy logic is used to recognize candlestick patterns and is applied to finanical forecasting. Candlestick patterns recognized by fuzzy logic give impact to the new model presented in this paper, and the results of stock market forecasting. In this paper, the daily stock quote of Exxon Mobile, General Electric, General Motors, Google, Microsoft, and Wells Farge are used as input data sets. The output of the model is the forecast of the next days closing price. For the new model, IF-THEN rule-based fuzzy logic is used for recognizing basic candlestick patterns. The performance of the previous study (Kamo and Dagli, 2006) is used for comparison of the data. The results of the models are evaluated on the basis of mean squared error. Graphs and charts bisually illustrate the trend generated by the new model and the actual stock market movement.


Engineering Management and Systems Engineering

Keywords and Phrases

Japanese Candlestick Pattern; Financial Forecasting; Fuzzy-Logic

Document Type

Article - Conference proceedings

Document Version


File Type





© 2007 American Society of Mechanical Engineers (ASME), All rights reserved.

This document is currently not available here.