Investment decision making by using fuzzy candlestick pattern and genetic algorithm

This paper proposed an approach to extract fuzzy candlestick patterns from financial time series and select a set of patterns for investment decision making. The candlestick chart in stock market is a widely used technical analysis model. The investor observes the candlestick chart and makes investment decisions by identifying patterns in the chart. We use fuzzy linguistic variables to model candlestick chart and extract patterns from the chart. A Genetic algorithm based approach is used to select a set of extracted pattern as the background knowledge in the system for investment decision making. The advantage of the proposed approach is the investment knowledge is comprehensible, editable, and visible. The user can set different range of historical financial time series to extract and select different set of patterns. The experimental results shows that the investment decisions based on selected fuzzy patterns have better investment performance than using original non-fuzzy patterns.