A new SAX-GA methodology applied to investment strategies optimization

Canelas, António; Neves, Rui; Horta, Nuno

doi:10.1145/2330163.2330310

Cited by 13 publications

(11 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As outlined by previous researches [14][15][16][17][18], the three major components of SAX algorithm involves: 1) Normalisation of the time series data, 2) Piecewise Aggregate Approximation (PAA) computation and 3) converting the PAA to a symbolic representation [14]. Performing the z-score normalization on the time series data (z i ) by subtracting each of the time series element (c i ) by the mean value (µ) and dividing it by the standard deviation (σ) as denoted in (1) is important to obtain meaningful comparison of the time series data as the data might have different offsets and amplitudes [14].…”

Section: Sax Time Series Analysismentioning

confidence: 77%

“…The SAX representation proves to be an excellent candidate as feature representation for forex data analysis as it is a simple yet powerful feature representation for such a huge set of data. The simple symbolic representation used initially for time series analysis has been adopted for stock investment strategies optimization [15][16][17][18]; focusing primarily on the analysis of stock market data. The processing algorithm involves the use of SaX features along with genetic algorithm optimization kernel which determines the buy/sell decisions.…”

Section: Sax Time Series Analysismentioning

confidence: 99%

See 1 more Smart Citation

An investigation into the recurring patterns of forex time series data

Yong

Lee

Ngo

2015

2015 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)

View full text Add to dashboard Cite

Abstract-Countless theories have been developed by both researchers and financial analyst in an attempt to explain the fluctuation of forex price. By obtaining an intimate understanding of the forex market, traders will hopefully be able to forecast and react to forex price oscillations on-the-fly towards making a profitable investment. In this paper, an investigation into the underlying theory that there exists repeating patterns within the time series data which forms the basis of technical analysis is conducted. The assumption that certain patterns do develop over time and the forex market does not fluctuate in a random manner is used to establish the fact that history repeats itself in forex trading. The patterns and repetitions unveiled within the forex historical data would be an important element for forex forecasting.

show abstract

Section: Sax Time Series Analysismentioning

confidence: 77%

Section: Sax Time Series Analysismentioning

confidence: 99%

An investigation into the recurring patterns of forex time series data

Yong

Lee

Ngo

2015

2015 IEEE International Symposium on Robotics and Intelligent Sensors (IRIS)

View full text Add to dashboard Cite

show abstract

“…A Novel Trend Symbolic Aggregate Approximation for Time Series 5 continuity of time series data, the ending point of a segment is the starting point of the following segment. Therefore, we only need to add a trend feature to each of the sequence segments to indicate the trend of the segment.…”

Section: Symbolic Representationmentioning

confidence: 99%

“…Therefore, the SAX representation speeds up the data mining process of time series data while maintaining the quality of the mining results. The SAX has been widely used for applications in various domains such as mobile data management [4], financial investment [5] and shape discovery [6]. SAX is based on Piecewise Aggregate Approximation (PAA) [7], so, it has a major limitation inherit from PAA on dimensionality reduction.…”

Section: Introductionmentioning

confidence: 99%

A Novel Symbolic Aggregate Approximation for Time Series

Zhu

Wan

et al. 2019

Advances in Intelligent Systems and Computing

View full text Add to dashboard Cite

Symbolic Aggregate approximation (SAX) is a classical symbolic approach in many time series data mining applications. However, SAX only reflects the segment mean value feature and misses important information in a segment, namely the trend of the value change in the segment. Such a miss may cause a wrong classification in some cases, since the SAX representation cannot distinguish different time series with similar average values but different trends. In this paper, we present Trend Feature Symbolic Aggregate approximation (TFSAX) to solve this problem. First, we utilize Piecewise Aggregate Approximation (PAA) approach to reduce dimensionality and discretize the mean value of each segment by SAX. Second, extract trend feature in each segment by using trend distance factor and trend shape factor. Then, design multi-resolution symbolic mapping rules to discretize trend information into symbols. We also propose a modified distance measure by integrating the SAX distance with a weighted trend distance. We show that our distance measure has a tighter lower bound to the Euclidean distance than that of the original SAX. The experimental results on diverse time series data sets demonstrate that our proposed representation significantly outperforms the original SAX representation and an improved SAX representation for classification.

show abstract

“…While there are numerous external factors affecting the Forex trading daily which can be classified into one of the categories in Fig 1, [11], [12] have also started looking into other feature representation which provides a more elegant solution whereby a more compact feature representation for prediction (SAX) can be obtained with faster computation which is important when dealing with a huge dataset. It has also later been expanded to include multi-dimensional information financial time series information [13].…”

Section: Technical Analysismentioning

confidence: 99%

Technical Indicators for Forex Forecasting: A Preliminary Study

Yong

Ngo

Lee

2015

Advances in Swarm and Computational Intelligence

View full text Add to dashboard Cite

Abstract. Traders and economists are often at odds with regards to the approach taken towards Forex financial market forecasting. Methods originating from the Artificial Intelligence (AI) area of study have been used extensively throughout the years in predicting the trading pattern as it is deemed to be robust enough to handle the uncertainty associated with Forex trading time series data. Herein this paper, the effects of different input types, in particular: close price as well as various technical indicators derived from the close price are investigated to determine its effects on the Forex trend predicted by an intelligent machine learning module.

show abstract

A new SAX-GA methodology applied to investment strategies optimization

Cited by 13 publications

References 12 publications

An investigation into the recurring patterns of forex time series data

An investigation into the recurring patterns of forex time series data

A Novel Symbolic Aggregate Approximation for Time Series

Technical Indicators for Forex Forecasting: A Preliminary Study

Contact Info

Product

Resources

About