ARIMA model has a strong potential for short-term prediction of stock market trends.

MLP techniques to get the real stock price movements and public sentiments.

Hidden Markov Model first proposed by Baum and Egon, which is a kind of Markov Chain and is used for the
pattern recognition technique. This paper finds the hidden relationship existing between the Hidden Markov Model
and stock prices. The experimental results show that, this method can get attractive accurate result, particularly
efficient in short period prediction.

APST, which performs the pre-processing of verifiable stock time arrangement information to produce the grouping
of approximated values by utilizing multi-scale segment mean methodology. To locate the closest neighbor objects
they utilize the Euclidian separation way to recognize the comparative arrangement of articles. The experimental
results of this system show that the executed framework has shown 74% of the exactness.

Artificial Neural Networks (ANNs) model is very popular due to its ability to learn patterns from data and infer
solution from unknown data.

QuantMod
It refers to the Quantitative financial Modeling which is used in financial time series data analysis.

The OHLC data is not directly downloaded from the Google finance (finance.google.com), instead a call to
getSymbols(Symbols, src='google') in-turn call this method.

Artificial Neural Network techniques to predict the stock price of companies. An Artificial Neural Network
(ANN), often just called a neural network, is a set of interconnected links that have
weights associated with them. The concept of ANN was derived from biological neural networks. Neural networks
open up a new foray into the field of making efficient and usable predictions in order to optimize profits. Artificial
Neural Networks are being used in numerous areas, as it is an irrefutably effective tool that aids the scientific
community in forecasting about probable outcomes.

MLP Neural Network

Multi Layer perceptron (MLP) is a feedforward neural network with one or more layers between input and output
layer. MLP maps sets of input data onto a set of appropriate outputs. Feedforward means that data flows in one
direction from input to output layer (forward). An MLP consists of multiple layers of nodes in a directed graph, with
each layer fully connected to the next one. Except for the input nodes, each node is a neuron (or processing element)
with a nonlinear activation function. This type of network is trained with the backpropagation learning
algorithm. MLPs are widely used for pattern classification, recognition, prediction and approximation. Multi Layer
Perceptron can solve problems which are not linearly separable. MLPs separate classes via Hyperplanes. MLPs use
distributed learning. MLPs have one or more hidden layers.

multilayer
perceptron (MLP) Neural Network technique.

Developing MLP neural network algorithm to predict future stock price.

With Neural Network Toolbox MATLAB, MLP neural network is built and trained for different combinations of
data and parameters
 deep learning-based regression models using long-and short-term memory (LSTM) networks with a novel approach of walk-
forward validation. Using the grid-searching technique, the hyperparameters of the LSTM models are optimized so that it is
ensured that validation losses stabilize with the increasing number of epochs, and the convergence of the validation accuracy is
achieved. We exploit the power of LSTM regression models in forecasting

Stock Price Prediction, Regression, Long and Short-Term Memory Network, Walk-Forward Validation, Multivariate Time
Series.

By analyzing the sentiments in the social media and utilizing the sentiment-related information in a non-linear
multivariate regression model based on self-organizing fuzzy neural networks (SOFNN)

convolutional neural network (CNN)-based models, for achieving a high level of accuracy and robustness in
forecasting on a multivariate financial time series data

The propositions in the second category utilize the concepts of time series and other econometric techniques like
autoregressive integrated moving average (ARIMA), Granger Causality Test, autoregressive distributed lag (ARDL),
vector autoregression (VAR), and quantile regression to forecast stock prices

The approach is called multi-step forecasting with walk-forward validation [27]. Following this approach, we build
the models using the records in the training dataset and then deploy the model for forecasting

we designed and evaluated eight machine learning-based regression models. These models are: (i) multivariate
linear regression, (ii) multivariate adaptive regression spline (MARS), (iii) regression tree, (iv) bootstrap aggregation
(Bagging), (v) extreme gradient boosting (XGBoost), (vi) random forest (RF), (vii) artificial neural network (ANN), and
(viii) support vector machine (SVM)

In one of our previous work, we demonstrated the efficacy and effectiveness of convolutional neural networks
(CNNs) in forecasting time series index values [28]. In this work, we have utilized the predictive power of another
deep learning model – long- and short-term memory (LSTM) networks - in forecasting on a complex multivariate
time series like the NIFTY 50 series. LSTM is a special type of recurrent neural networks (RNNs) – neural networks
that allow feedback loops to communicate data from a node in a forward layer to a node in a backward layer.

The architecture of LSTM networks integrated with the backpropagation through time (BPTT) algorithm for learning
the parameters provides these networks with a high degree of power in forecasting in univariate and multivariate
time series

The four models are: (i) LSTM model for multi-step forecasting with univariate input data of one week, (ii) LSTM
model for multi-step forecasting with univariate input data of two weeks, (iii) Encoder-decoder LSTM for multi-step
forecasting with univariate input data for two weeks, and (iv) Encoder-decoder LSTM for multi-step forecasting with
multivariate input data for two weeks.
generative adversarial networks (GANs) in time series analysis and forecasting of stock prices.

ARIMA is a statistical model which is known to be efficient for time series forecasting especially for short-term prediction. In
this paper, we propose a model for forecasting the stock market trends based on the technical analysis using historical stock
market data and ARIMA model. This model will automate the process of direction of future stock price indices and provides
assistance for financial specialists to choose the better timing for purchasing and/or selling of stocks.

efficient market hypotheses (EMH) that was put forward by Fama (1990). The EMH is considered as
bridging the gap between financial information and the financial market; it also affirms that the
fluctuations in prices are only a result of newly available information; and that all available information
reflected in market prices. The EMH assert that stocks are at all times in equilibrium and are difficult for
inventors to speculate.

The kNN algorithm method is used on the stock data. We adopted an efficient prediction algorithm tool
of kNN with k=5 to perform such tests on the training data sets we had. According to the results, kNN
algorithm was stable and robust with small error ratio, so the results were rational and reasonable. In
addition, depending on the actual stock prices data; the prediction results were close to actual prices.
Having such rational results for predictions in specific, and for using data mining techniques in real life;
this presents a good indication that the use of data mining techniques could help decision makers at
various levels when using kNN for data analysis.

the authors have focused on stock market

data’s preprocessing with the help of HIVE, Hadoop
ecosystem. HIVE can do work extremely fast as it divides
the query in several map-reduce job which can be
executed in parallel as well as it can store large amount of
data easily with the help of HDFS. Thus, HIVE is much
more effective than any other relational database system.
Further, the stock price prediction is based on the
sentiment analysis of news headlines and historical stock
data.

The literature is
geared towards making money from stock price movements,
and various indicators like Bollinger Band, Moving Average
Convergence Divergence (MACD), Relative Strength Index
(RSI), Moving Average, Momentum Stochastics, Meta Sine
Wave etc., have been devised towards this end. There are
also patterns like Head and Shoulders, Triangle, Flag,
Fibonacci Fan, Andrew's Pitchfork etc., which are
extensively used by traders for gain. These approaches
provide the user with visual manifestations of the indicators
which helps the ordinary investors to understand which way
stock prices may move.

as the two inputs a fuzzy neural

network-based SOFNN algorithm. The performance of this
sentiment analysis-enhanced model is found to be the best
among all models in its ability to accurately forecast the
stock price movement of NIFTY 50. The study has
conclusively proved that public sentiments in the social
media serve as a very significant input in predictive model
building for stock price movement.

a highly flexible non-linear modeling technique ANN has been implemented to forecast the stock prices of selected
sectors and companies under Bombay Stock Exchange.

MI-LSTM
achieves an improvement of 9:96% compared with LSTM in terms of mean square
error (MSE). we propose an improved MI-LSTM based on LSTM and attention mechanism,
which achieves better performance in extracting potential information and _ltering noise.
MI-LSTM units assign di_erent weights to di_erent input series to keep the dominant status
of mainstream, while absorbing information from leaky input gates. The output of MILSTM
is further processed using temporal self-attention. Based on these stage attentions,
our model can not only focus on the most important factors but also adaptively capture
the most relevant time steps. By employing 3 additional factors and Gaussian noise, we
design experiments to prove our improvements over both original LSTM and DA-RNN.