I'm intrested in forecasting Stock market data. I tried to predict the close price and volume seperately using ARIMA, but not got a better result. So I tried with LSTM model. If I want to perform a multivariate analysis, considering the co-relation of both variables, which are the best multivariate analysis techniques?
Hi
How many variables you have and what is the length of your time series.
If the price in the stock market could be predicted with great accuracy, investors and investment advisers would make everyone rich. The best one can do is to estimate the expected values with some error, but as for forecasting to have any practical application (investment decision), even sophisticated software cannot capture market movement with satisfactory level of accuracy. Why? Stock price movement is mostly random. Instead of studying the stock price individually, it may be better to look at index of that market. As an academic exercise, it may be an intersting subject, but as a decision aid no model could really capture its future movement..... the value of the stock market in the long run keeps increasing that much we know because we look at past data and plot it over time. However, how much will it move tomorrow? An economist is no better than a fortune teller or card reader in answering that question.
I have 7 variables and the series consists of 5 years data on a daily wise. @Abbas Lafta Kneehr
Stock market is a random walk and can not be predicted.
I know this information will not stop anyone from trying but result will be the same for any technique - loss after accounting for all transaction costs.
- Badges
- Science topic
- Similar topics
- Geoscience
- Asia
- India