A deep learning approach for financial market prediction: utilization of Google trends and keywords

  • Min-Hsuan Fan
  • Mu-Yen ChenEmail author
  • En-Chih Liao
Original Paper


This study used the amount of Internet search on Google Trend and analyzed the correlation between the search volume on Google Trend and Taiwan Weighted Stock Index. The keyword search volume provided by Google Trend was used in the correlation test and the unit root test. Then, the keywords obtained were analyzed in two experiments—first, machine learning, and second, search trend. After empirical analysis, it was found that neural network in experiment one performed better than support vector machine and decision trees. Therefore, neural network was selected to compare with the search trend in the second experiment. Through comparative analysis of calculation of return values, it was found that the return value in search trend is higher than that of the neural network. Therefore, this paper revealed that there was a correlation between using company names of Taiwan 50 Index as search keywords and the rise and fall of TAIEX index.


Google trends TAIEX Search volume Artificial neural network 



  1. Bijl L, Kringhaug G, Molnár P, Sandvik E (2016) Google searches and stock returns. Int Rev Financ Anal 45:150–156Google Scholar
  2. Breiman L, Friedman J, Stone CJ, Olshen RA (1984) Classification and regression trees. CRC Press, Boca Raton. zbMATHGoogle Scholar
  3. Chang CC, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol 2(3):27. Google Scholar
  4. Chatzis SP, Siakoulis V, Petropoulos A, Stavroulakis E, Vlachogiannakis N (2018) Forecasting stock market crisis events using deep and statistical machine learning techniques. Expert Syst Appl 112:353–371. Google Scholar
  5. Chen SM, Chang YC (2011) Weighted fuzzy rule interpolation based on GA-based weight-learning techniques. IEEE Trans Fuzzy Syst 19(4):729–744. MathSciNetGoogle Scholar
  6. Chen MY, Chen BT (2015a) A hybrid fuzzy time series model based on granular computing for stock price forecasting. Inf Sci 294:227–241. MathSciNetGoogle Scholar
  7. Chen SM, Chen SW (2015b) Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups and the probabilities of trends of fuzzy logical relationships. IEEE Trans Cybern 45(3):405–417. Google Scholar
  8. Chen MY, Chen TH (2019) Modeling public mood and emotion: blog and news sentiment and socio-economic phenomena. Future Gener Comput Syst 96:692–699. Google Scholar
  9. Chen SM, Huang CM (2003) Generating weighted fuzzy rules from relational database systems for estimating null values using genetic algorithms. IEEE Trans Fuzzy Syst 11(4):495–506. Google Scholar
  10. Chen SM, Jian WS (2017) Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups, similarity measures and PSO techniques. Inf Sci 391–392:65–79. Google Scholar
  11. Chen SM, Wang JY (1995) Document retrieval using knowledge-based fuzzy information retrieval techniques. IEEE Trans Syst Man Cybern 25(5):793–803. Google Scholar
  12. Chen SM, Chu HP, Sheu TW (2012) TAIEX forecasting using fuzzy time series and automatically generated weights of multiple factors. IEEE Trans Syst Man Cybern Part A Syst Humans 42(6):1485–1495. Google Scholar
  13. Chen MY, Fan MH, Chen YL, Wei HM (2013a) Design of experiments on neural network’s parameters optimization for time series forecasting in stock markets. Neural Netw World 23(4):369–393. Google Scholar
  14. Chen SM, Manalu GM, Pan JS, Liu HC (2013b) Fuzzy forecasting based on two-factors second-order fuzzy-trend logical relationship groups and particle swarm optimization techniques. IEEE Trans Cybern 43(3):1102–1117. Google Scholar
  15. Chen MY, Liao CH, Hsieh RP (2019) Modeling public mood and emotion: Stock market trend prediction with anticipatory computing approach. Human Behav, Comput. Google Scholar
  16. Cheng SH, Chen SM, Jian WS (2016) Fuzzy time series forecasting based on fuzzy logical relationships and similarity measures. Inf Sci 327:272–287. MathSciNetzbMATHGoogle Scholar
  17. Chong E, Han C, Park FC (2017) Deep learning networks for stock market analysis and prediction: methodology, data representations, and case studies. Expert Syst Appl 83(15):187–205. Google Scholar
  18. Chumnumpan P, Shi X (2019) Understanding new products’ market performance using Google Trends. Aust Market J 5:6. Google Scholar
  19. Cortes C, Vapnik V (1995) Support-vector networks. Mach Learn 20(3):273–297. zbMATHGoogle Scholar
  20. Dewan V, Sur H (2018) Using Google trends to assess for seasonal variation in knee injuries. J Arthrosc Joint Surg 5(3):175–178. Google Scholar
  21. Dickey DA, Fuller WA (1979) Distribution of the estimators for autoregressive time series with a unit root. J Am Stat Assoc 74(366a): 427–431.
  22. Elliott RN (1938) The Wave Principle. Republished (1980, 1994). In: Prechter RR (ed), R.N. Elliott's Masterworks. New Classics Library, Gainesville, GA, p 144Google Scholar
  23. Fan MH, Liao EC, Chen MY (2014) A TAIEX forecasting model based on changes of keyword search volume on Google Trends. In: 2014 IEEE International Symposium on Independent Computing (IEEE ISIC 2014), Orlando, FL, USA, December 9-12, 96-99Google Scholar
  24. Granger CW, Newbold P (1974) Spurious regressions in econometrics. J Econ 2(2):111–120. zbMATHGoogle Scholar
  25. Grodinsky J (1953) Investments. Ronald Press Company, New YorkGoogle Scholar
  26. Hu H, Tang L, Zhang S, Wang H (2018) Predicting the direction of stock markets using optimized neural networks with Google Trends. Neurocomputing 285:188–195. Google Scholar
  27. Joseph K, Babajide Wintoki M, Zhang Z (2011) Forecasting abnormal stock returns and trading volume using investor sentiment: evidence from online search. Int J Forecast 27(4):1116–1127. Google Scholar
  28. Lee LW, Chen SM (2008) Fuzzy risk analysis based on fuzzy numbers with different shapes and different deviations. Expert Syst Appl 34(4):2763–2771. Google Scholar
  29. Long W, Lu Z, Cui L (2019) Deep learning-based feature engineering for stock price movement prediction. Knowl Based Syst 164:163–173. Google Scholar
  30. Nelson CR, Plosser CR (1982) Trends and random walks in macroeconomic time series: some evidence and implications. J Monet Econ 10(2):139–162. Google Scholar
  31. Phillips PC, Perron P (1988) Testing for a unit root in time series regression. Biometrika 75(2): 335-346.
  32. Preis T, Moat HS, Stanley HE (2013) Quantifying trading behavior in financial markets using Google Trends Scientific reports 3Google Scholar
  33. Quinlan JR (1993) C4. 5: programs for machine learning (Vol. 1). Morgan kaufmannGoogle Scholar
  34. Resnick P, Iacovou N, Suchak M, Bergstrom P, Riedl J (1994, October). GroupLens: an open architecture for collaborative filtering of netnews. In: Proceedings of the 1994 ACM conference on Computer supported cooperative work (pp. 175-186). ACMGoogle Scholar
  35. Robert R (1932) The Dow theory: an explanation of its development and an attempt to define its usefulness as an aid in speculation. Barron's, New YorkGoogle Scholar
  36. Rumelhart DE, Hinton GE, Williams RJ (1986) Learning Internal Representations by Error Propagation, Parallel Distributed Processing, Explorations in the Microstructure of Cognition, ed. DE Rumelhart and J. McClelland. Vol. 1Google Scholar
  37. Said SE, Dickey DA (1984) Testing for unit roots in autoregressive-moving average models of unknown order. Biometrika 71(3): 599-607.
  38. Smith GP (2012) Google internet search activity and volatility prediction in the market for foreign currency. Finance Res Lett 9(2):103–110. Google Scholar
  39. Song Q, Chissom BS (1993) Forecasting enrollments with fuzzy time series—part I. Fuzzy Sets Syst 54(1):1–9. Google Scholar
  40. Song Q, Chissom BS (1994) Forecasting enrollments with fuzzy time series–Part II. Fuzzy Sets Syst 62(1):1–8. Google Scholar
  41. Takeda F, Wakao T (2014) Google search intensity and its relationship with returns and trading volume of Japanese stocks. Pacific-Basin Finance J 27:1–18. Google Scholar
  42. Yu L, Zhao Y, Tang L, Yang Z (2019) Online big data-driven oil consumption forecasting with Google trends. Int J Forecast 35(1):213–223. Google Scholar
  43. Zadeh LA (1965) Fuzzy sets. Inf Control 8(3):338–353. zbMATHGoogle Scholar
  44. Zeng S, Chen SM, Teng MO (2019) Fuzzy forecasting based on linear combinations of independent variables, subtractive clustering algorithm and artificial bee colony algorithm. Inf Sci 484:350–366. Google Scholar

Copyright information

© Springer Nature Switzerland AG 2019

Authors and Affiliations

  1. 1.National Taichung University of Science and TechnologyTaichungTaiwan

Personalised recommendations