The Evolution of S & P 500 Index, Forecasted Using an Autoregressive Integrated Model
Abstract
The indexes Standard&Poor’s and Dow Jones Industrial Average were each, along time, the benchmarks of the American stock exchange. But lately, the first one gained the advantage, because it is composed of the stocks from multiple companies, carefully chosen on the base of strict criteria. Hence, its evolution is interesting, due to many reasons. The present article makes a forecast for S&P 500’s value on a 30-day period, with input data covering 1 year. The forecast is constructed on an autoregressive integrated model, because this type of model proved to be adequate for short- and medium-term periods.  The offered results are compaired in the end with the real values of the index, in order to see how accurate is the estimation. The conclusions will either confirm once again, or will refute the ability of the autoregressive model to forecast future values, but they will be 100% true only for the studied context.
Keywords: Index, S&P 500, Forecast, Benchmark, Criteria.
References
Adebiyi A. Adewumi, Ayo CK (2014) Stock Price Prediction Using the ARIMA Modelâ€, UKSim-AMSS 16th International Conference on Computer Modelling and Simulation.
Cao L, Tay F (2001) Financial forecasting using vector machines, Neural Computer Appl., 184-192,
Demuth H, Beale M (1998) Neural network toolbox: For use with MATLAB, Natick, MA: The Math Works, Inc.,
Hosseini H, Luo D, Reynolds K (2006) The comparison of different feed forward neural network architectures for ECG signal diagnosis, Medical Eng. Phys., 372-378.
Javier E. Rosario, Francisco N, Antonio J (2003) ARIMA Models to Predict Next Electricity Price, IEEE Transactions on Power Systems, 18:1014-1020.
Lam M (2004) Neural network techniques for financial performance prediction: Integrating fundamental and technical analysis, Decis Support Syst., 567-581.
Mondal P, Shit L, Goswami S (2014) Study of Effectiveness of Time Series Modeling (ARIMA) in Forecasting Stock Pricesâ€, International Journal of Computer Science, Engineering and Applications (IJCSEA), vol.4,
O’Connor N, Madden M (2006) A neural network approach to predicting stock exchange movements using external factors, Knowl. Base Syst., 371-378.
Pieleanu F (2016) Comparative study in estimating Volkswagen’s price: ARIMA versus ANNâ€, sent for publishing.
Pieleanu F (2016) Predicting the evolution of BET index, using an ARIMA model, sent for publishing, 2016
Saxena P, Merh N, Pardasani R (2010) A comparison between hybrid approaches of ANN and ARIMA for Indian stock trend forecastingâ€, Journal of Business Intelligence, 3:23-43.
Vanstone G Finnie (2009) An empirical methodology for developing stock market trading systems using artificial neural networksâ€, Expert System Appl., 6668-6680.
Yao J, Tan L, Poh H (1992) Neural networks for technical analysis: a case study on KLCIâ€, International Journal of Theoretical and Applied Finance, 221-241.
Zhang G, Patuwo B, Hu Y (1998) Forecasting with artificial neural networks: the state of the artâ€, International Journal of Forecasting, 35-62.
https://research.stlouisfed.org/fred2/series/SP500/downloaddata
