Categories	Subcategories	Definition
1. Neural networks/ algorithms used in research	A-LSTM	Stock price projection with the—RNN LSTM.
	B-Compared to LSTM	Stock price prediction with other artificial neural networks and results compared to RNN LSTM.
	C-Combined with LSTM	Predict stock prices with blended neural networks including LSTM.
	D-Others	Other topics unrelated to subcategories 1A to 1C.
2. Types of data analyzed	A-Closing prices	Daily stock closing prices.
	B-Opening prices	Daily stock opening prices.
	C-Highest and lowest prices	Daily highest and lowest stock prices.
	D-Volumes	Stock trading volumes.
	E-Index	Daily closing of the Stock Price Index.
	F-Others	Others not related to subcategories 2A to 2E.
3. Analysis period	A-Up to 5 years	Data from 0 to 5 years.
	B-More than 5 to 10 years	Data from 5.1 to 10 years.
	C-More than 10 years	More than 10 years.
	D-Not applicable/not informed	Studies that do not inform the period of analysis.
4. Objectives	A-Tests with new neural networks models	Improved share price accuracy tested with other neural networks algorithms and/or hybrid models.
	B-Tests with other assets	Check whether using price and volatility indices of other assets (except stocks) can help predict stock prices.
	C-Sentiment Analysis	Improved accuracy in stock price projection with sentiment analysis.
	D-Others	Other topics unrelated to subcategories 7A to 7C.
5. Data origin	A-NYSE, NASDAQ, DJI, S&P, CBOE, FTSE	US Stock Exchanges.
	B-CSI, SSE, NSE, HS, SH, SZSE	China and Hong Kong Stock Exchanges.
	C-B3	Brazil Stock Exchange.
	D-TWSE	Thailand Stock Exchange.
	E-IMKB	Turkey Stock Exchange.
	F-TSE	Tehran Stock Exchange.
	G-GSE	Ghana Stock Exchange.
	H-ASX	Australia Stock Exchange.
	I-DAX	Germany Stock Exchange.
	J-KOSPI, KOSDAQ	Korea Stock Exchanges.
	K-NSE	India Stock Exchange.
	N-NIKKEI	Japan Stock Exchange.
	O-IDX	Indonesia Stock Exchange.
	P-FTSE	UK Stock Exchange.
	L-Texts	News agencies/websites, for sentiment analysis.
	M-No information or other	There is no identification of information that can be considered as inputs for the evaluation models.
6. Results	A-Outperforms compared methods	The results of the proposed model surpass the results of the compared model(s).
	B-Promising model	The results of the proposed model are promising.
	C-Others	Other results unrelated to subcategories 8A to 8B.
7. Conclusions	A-New conclusions	Presentation of new findings—adjustment to already tested neural networks models, improvement in the quality of input information, and other innovations to existing models.
	B-New perspectives	Presentation of a new theory, new models of projections, with models of isolated, hybrid or combined neural networks.
	C-Conclusions similar to works presented previously	Studies that do not present new perspectives or new conclusions.
	D-Others	Other results unrelated to subcategories 9A to 9C.
8. Pathways for future studies	A-Hybrid models with LSTM	Studies with other hybrid models using LSMT.
	B-Other ANN	Studies with other ANN, pure or hybrid.
	C-Other types of data	In addition to opening, closing, high, low and trading volume data, sentiment analysis tests with other types of news and stock data, in periods such as intraday.
	D-Data from other sources	Study the model’s performance on other Stock Exchanges.
	E-Other analysis periods	Study and test data from different periods.
	F-No path commented by the author(s)	No future path detailed by author(s).