# Tag Info

0

Reuters has historical financial news that goes back pretty far. I was doing some similar stuff with historical news and you can go back before 1950's, for certain companies. You can scrape from them using a scraper built by yourself (very easy to implement in python) or using a service like Kimono, which you can set to run every so often. Kimono also lets ...

1

I think this project could be interesting! This is because, although already exist market data sources (see QUANDL) for free or cheap, I think it would be nice build your own database. Moreover, I find the fact you want to build an updated dataset about companies news, report & releases extremely interesting, since a serious source about historical ...

1

I suggest you to implement all the analysis you cited above and analyze the results choosing the best model on model performance measures, as, for instance, the model $R^2$ value, the AIC (BIC) value, etc.; this should be the proper way to develop a model. As regards your question particularly, the literature about the topic suggest to develop the model on ...

2

Basic rules for what you want to follow to have a meaningfull result 1 All your variables should be in the same terms 2.All your regression variables should be stationary (weak sense stationary) - check if there are long term dependencies 3.Test for multi-collinearity / Serial correlation / Homocedasticity each variable against the predictor.

1

Although I think your question will be flagged for "basic knowledge" you can find free sources for this data including Yahoo Finance, Quandl. Commercial data vendors also provide this information. However, you really need to define what sort of data you are trying to find. Spot prices (for physical delivery), spot prices (for cash settled) or futures data ...

Top 50 recent answers are included