Forecasting variance of NiftyIT index with RNN and DNN

Abstract

A time series is an order of observations engaged serially in time. The prime objective of time series analysis is to build mathematical models that provide reasonable descriptions from training data. The goal of time series analysis is to forecast the forthcoming values of a series based on the history of the same series. Forecasting of stock markets is a thought-provoking problem because of the number of possible variables as well as volatile noise that may contribute to the prices of the stock. However, the capability to analyze stock market leanings could be vital to investors, traders and researchers, hence has been of continued interest. Plentiful arithmetical and machine learning practices have been discovered for stock analysis and forecasting/prediction. In this paper, we perform a comparative study on two very capable artificial neural network models i) Deep Neural Network (DNN) and ii) Long Short-Term Memory (LSTM) a type of recurrent neural network (RNN) in predicting the daily variance of NIFTYIT in BSE (Bombay Stock Exchange) and NSE (National Stock Exchange) markets. DNN was chosen due to its capability to handle complex data with substantial performance and better generalization without being saturated. LSTM model was decided, as it contains intermediary memory which can hold the historic patterns and occurrence of the next prediction depends on the values that preceded it. With both networks, measures were taken to reduce overfitting. Daily predictions of the NIFTYIT index were made to test the generalizability of the models. Both networks performed well at making daily predictions, and both generalized admirably to make daily predictions of the NiftyIT data. The LSTM-RNN outpaced the DNN in terms of forecasting and thus, grips more potential for making longer-term estimates.

Analyzing the performance of long short‐term memory architectures for malware detection models

“…The DNN has high prediction performance (especially when the true data has clear trends). LSTM‐RNN has high performance with variations in the true data 18 …”

Machine intelligence in dynamical systems: \A state‐of‐art review

“…In a Stock Market trading simulation, with the optimum number of hidden layers, PCA-DNN classifiers obtained the maximum classification accuracy and gave higher returns with fewer risks (variance). Karthik et al (2022) compared the daily variance of NIFTYIT in the BSE (Bombay Stock Exchange) and NSE (National Stock Exchange) markets using two powerful ANN models: DNN and Long Short-Term Memory (LSTM). DNN architecture was made of three hidden layers with 20, 18, and 21 neurons, respectively.…”

“…Karthik et al (2022) compared the daily variance of NIFTYIT in the BSE (Bombay Stock Exchange) and NSE (National Stock Exchange) markets using two powerful ANN models: DNN and Long Short‐Term Memory (LSTM). DNN architecture was made of three hidden layers with 20, 18, and 21 neurons, respectively.…”

Cybersecurity design of data-intensive systems

“…LSTM-RNN has high performance with variations in the true data. (Karthik et al, 2022) Recurrent Neural Network (RNN) and its variants (e.g., Echo State Networks) RNN is used in speech recognition and natural language processing, connectors between nodes form a directed graph along temporal sequence (Jaeger et al, 2001) (Gal et al, 2016) A convolutional neural network (CNN) can be applied as the first layer, and LSTM can be applied as the second layer (Gal et al, 2016) Malware detection methods could be categorized as static, dynamic, and hybrid as shown in Table 7.8. While malware detection methods assess the maliciousness of the software, the classification of the malware gives the probability of the malware belonging to a malware class/family.…”