KMITL

Permanent URI for this communityhttps://dspace.kmitl.ac.th/handle/kmitl/1

Browse

Settings

Subject: search.filters.subject.association rule

Search Results

Now showing 1 - 2 of 2
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    Gold-Price Forecasting Method Using Long Short-Term Memory and the Association Rule
    (2023-01-01)
    Boongasame, Laor
    ;
    Viriyaphol, Piboonlit
    ;
    Tassanavipas, Kriangkrai
    ;
    Temdee, Punnarumol
    Since gold prices influence international economic and monetary systems, numerous studies have been conducted to forecast gold prices. Nonetheless, studies employing the linear relationship method usually fail to explain the change in the pattern of the gold price. This study introduces a new paradigm that incorporates association rules and long short-term memory (LSTM) as a nonlinear-based method. For simulation, the proposed method was analyzed with data from Yahoo Finance from January 2010 to December 2020. The association rule was used to choose features relevant to the gold spot (GS) in the US Dollar Index (DXY). The LSTM forecast the gold price with a range of hyperparameter settings. The simulation results showed that the proposed method—the LSTM with GS and DXY, or LSTM-GS-DXY—resulted in low mean absolute percentage error (MAPE) metrics. In addition, the proposed LSTM-GS-DXY system outperformed the simple moving average (SMA), weight moving average (WMA), exponential moving average (EMA), and auto-regressive integrated moving average (ARIMA).
      1
  • Loading...
    Thumbnail Image
    Some of the metrics are blocked by your 
    consent settings
    Item type:Publication,
    An application of association rule mining based on stock market
    (2011-12-01)
    Srisawat, Anantaporn
    Stock trading is a popular approach for money investment. This paper focuses on Thai stock market which has hundreds of individual stocks. The aim of this paper is to apply an association rule mining technique for discovering the relationships between individual stocks. The transactional dataset used to generate the rules consists of 242 trading days from 4 January 2010 to 30 December 2010. The results from the discovered association rules can indicate the trends of related individual stocks. In addition, these rules may help beginner stock traders to preliminary select interesting stocks for further analysis. © 2011 AICIT.