فايل دانشگاهی – بررسی عوامل موثر بر قیمت طلا و ارائه مدل پیش بینی قیمت …

FINDING IMPORTANT FACTORS EFFECTING THE GOLD PRICE AND BUILDING THE PREDICTOR MODEL USING DATA MINING TECHNIQUES
BY
MINOO DELJAVAN ANVARY
During history gold has attracted people’s attention as a precious metal; therefore, predicting its price is a prominent issue. Precise investigation of factors which affect gold price plays a significant role in increasing precision of our prediction. In this study more effective factors are considered compared to previous researches. Collected data is divided into three classes from time schedule perspective; daily, monthly and annually. Experiments revealed that the precision of our predictions is improved 2%, 7.3% and 5.6% compared to neural network, time series and linear regression methods, respectively. Obtained results demonstrate marvelous performance of investigated factors in gold price prediction. The results will lead to more benefits for people, organizations and jewelers. At the end some suggestions for future research are presented.
KEYWORDS: Data Mining , Factors Affecting Forecast , Time Series , Neural Network, Regression Methods , Forecast Accuracy.
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” alt=”Description: Z:zareiarm-2.JPG” />

Shiraz University
Faculty of e-Learning
M.S.Thesis
In Information Technology Engineering (e-Commerce)
FINDING IMPORTANT FACTORS EFFECTING THE GOLD PRICE AND BUILDING THE PREDICTOR MODEL USING DATA MINING TECHNIQUES
By
MINOO DELJAVAN ANVARY
Supervised by
Dr. A. Sami

  1. . The Classical Gold Standard
    ۲. Bordo ↑
  2. . Consumer Price Index ↑
  3. . Harmonised Indices of Consumer Prices ↑
  4. . Exchange Traded Funds ↑
  5. . Standard and Poor’s Depository Receipt ↑
  6. . Gross domestic product

  7. . Tehran exchange price index ↑
  8. . the traditional equal weight ↑
  9. . the variance covariance matrix ↑
  10. . the odd matrix ↑
  11. . multi liner regression ↑
  12. . advanced regression ↑
  13. . Nearest Neighbours ↑
  14. . Multilayer Perceptron ↑
  15. . Higher Order Neural Networks ↑
  16. . Multiple Linear Regression ↑
  17. . universal functional approximators ↑
  18. ۱- Adaptive Neuro-Fuzzy Inference System
    این مطلب را هم بخوانید :  جستجوی مقالات فارسی - شناسایی و اولویت بندی عوامل موثر بر جذب مشتریان۹۰- قسمت ۴۴