Editors Choice – Stock Market Prediction Based on Technical-Deviation-ROC Indicators Using Stock and Feeds Data

Author(s):Deepika N. and P. Victer Paul*

Volume 15, Issue 3, 2022

Published on: 31 August, 2020

Article ID: e180322185408

Pages: 9

DOI: 10.2174/2666255813999200831120847


Background: The attempt of this research is to propose a novel approach for the efficient prediction of stock prices. The scope of this research extends by including the feature of sentiment analysis using the emotions and opinions carried by social media platforms. The research also analyzes the impact of social media, feeds data and Technical indicators on stock prices for the design of the prediction model.

Objectives: The goal of this research is to analyze and compare the models to predict stock trends by adjusting the feature set.

Methods: The basic technical and new momentum volatility indicators are calculated for the benchmark index values of the stock. The text summarization was applied on collected day-wise tweets for a particular company and then sentiment analysis was performed to get the sentiment value. All these collected features were integrated to form the final dataset and accuracy comparisons were made by experimenting with the algorithms- Support vector machine (SVM), Backpropogation and Long short-term memory (LSTM).

Results: The execution is carried out for each algorithm with 30 epochs. It is observed that the SVM exhibits 2.78%, Backpropogation exhibits 5.02% and LSTM exhibits 10.30 % enhanced performance than the prediction model designed using basic technical indicators. Moreover, along with human sentiment, the SVM provides 5.48%, Backpropogation 5.28% and LSTM 0.07% better accuracy. The standard deviation results are for SVM 1.59, for back propagation 2.46, and LSTM 0.19.

Conclusion: The experimental results show that the standard deviation of LSTM is less than the SVM and back propagation algorithms. Hence, obtaining steady accuracy is highly possible with LSTM. Read now: https://bit.ly/3vDiZ94

PRESS RELEASE – Molecular basis of neural memory — reviewing ‘neuro-mimetic’ technologies

This article by Dr. Gerard Marx and Dr. Chaim Gilon is published in Neuroscience and Biomedical Engineering, Volume 6, 2018


The overwhelming quest in cognitive science has been (and still is) to scientifically describe mental processes on a molecular level, notably memory and intelligence, and attempt to mimic them technologically. But really ‘intelligent’ computers can only arise from an appreciation of neural reality with credible principles about the nature of neural mentation.

A function called ‘Memory’ is central to the intelligence of both computers and brains, though each type arise from quite different processes. For example, computers processes (computation) and memory are well characterized theoretically (information theory) and practically (manufacture of memory chips). But as there is no binary code for emotions, the computer is deficient of any emotive quality. By contrast, biologic neurons and neural nets remember on the basis of multinary (not binary) processes. They experience emotive states that confer meaning (value) to all stimuli. But what are the details of the biologic neural process?

To clarify these, Marx & Gilon propose a tripartite mechanism of neural memory and provide a chemographic description. It involves the interactions of neurons with their surrounding extracellular matrix (nECM) and dopants, comprising trace metals (copper, zinc, etc) and neurotransmitters (more than 100 NTs). The NTs elicit both physiologic reactions and psychic states. Essentially, the neuron forms metal-centered complexes within the surrounding nECM, to encode cognitive units of information (cuinfo). Thus, neural memory is stored outside the highly extended cell, but readily available for recall.

Within that context, Marx & Gilon review the IBM Brain Chip and the Blue Brain Project, both being technologies which represent themselves as mimicking biologic neural systems, one as a chip, the other as a simulation. But both are found wanting, due to their inappropriate modeling of neuron morphology and the lack of emotive qualifiers. Consequently, the demotive IBM Brain Chip and the Blue Brain Simulation are inadequate actual and virtual constructs of neural systems and cannot be said to be truly ‘neuromimetic’.

Marx & Gilon propose a novel, but credible biochemical model, a tripartite mechanism for neural memory. This implies a ‘paradigm shift’ for cognitive science, a new way of thinking about mental processes. Expectedly, the tripartite model could help steer the development of technologies truer to neurobiology and neurochemistry.

For more information about the research, please visit: http://www.eurekaselect.com/159732



The Map of Emotions

Researchers found that the most common emotions trigger strong bodily sensations, and the bodily maps of these sensations were topographically different for different emotions. The sensation patterns were, however, consistent across different West European and East Asian cultures, highlighting that emotions and their corresponding bodily sensation patterns have a biological basis.

“Emotions adjust not only our mental, but also our bodily states. This way the prepare us to react swiftly to the dangers, but also to the opportunities such as pleasurable social interactions present in the environment. Awareness of the corresponding bodily changes may subsequently trigger the conscious emotional sensations, such as the feeling of happiness,” tells assistant professor Lauri Nummenmaa from Aalto University.Image

“The findings have major implications for our understanding of the functions of emotions and their bodily basis. On the other hand, the results help us to understand different emotional disorders and provide novel tools for their diagnosis.”

The research was carried out on line, and over 700 individuals from Finland, Sweden and Taiwan took part in the study. The researchers induced different emotional states in their Finnish and Taiwanese participants. Subsequently the participants were shown with pictures of human bodies on a computer, and asked to colour the bodily regions whose activity they felt increasing or decreasing.

The research was funded by European Research Council (ERC), The Academy of Finland and the Aalto University (aivoAALTO project)

The results were published on 31 December, 2013 in the scientific journal Proceedings of The National Academy of Sciences.


[Source: http://www.sciencedaily.com/releases/2013/12/131231094353.htm]

%d bloggers like this: