Data science approach to stock prices forecasting in Indonesia during Covid-19 using Long Short-Term Memory (LSTM)

Digital Therapy: Alleviating Anxiety and Depression in Adolescent Students During COVID-19 Online Learning - A Scoping Review

The learning method has changed from offline to online since Coronavirus Disease 2019 pandemic cause mental health problems in students such as stress, anxiety, and even depression. Interventions to reduce mental health problems in adolescents need to be carried out digitally to reduce the transmission of Coronavirus Disease 2019. The purpose of this study is to explore methods of digital therapy to reduce symptoms of anxiety and depression among students during the Coronavirus Disease 2019. A scoping review study design was used in this study. Database the study from CINAHL, PubMed, and Scopus databases. This study used PRISMA Extension for Scoping Reviews (PRISMA-ScR) and for quality appraisal used JBI Quality Appraisal. The inclusion criteria for articles in this study are full text, randomized control trial or quasi-experiment research design, English language, students sample, and the publication period during COVID-19 pandemic (2019-2022). There were found 13 articles discussing digital therapy and it was found that the digital therapy model to reduce anxiety and depression includes directions through digital modules, directions via video, and asynchronous discussions via online meeting. The sample range in this study is 37-1986 students. Most of the articles come from developed countries. Delivery services of digital therapy consist of three phases, namely psycho-education, problem-solving, and implementation of problem-solving strategies. The authors found that there are four digital therapy methods, namely Improving psychological abilities, Bias-modification intervention, Self-help intervention, and Mindfulness intervention. The implementation of digital therapy must still pay attention to various aspects that affect students, so that therapists need to pay attention to physical, psychological, spiritual, and cultural aspects. Here we highlight, digital therapy interventions are proven for improving mental health by reducing depression and anxiety levels among students during the COVID-19 pandemic by paying attention to all aspects that affect students.

Stock trend prediction using sentiment analysis

These days, the vast amount of data generated on the Internet is a new treasure trove for investors. They can utilize text mining and sentiment analysis techniques to reflect investors' confidence in specific stocks in order to make the most accurate decision. Most previous research just sums up the text sentiment score on each natural day and uses such aggregated score to predict various stock trends. However, the natural day aggregated score may not be useful in predicting different stock trends. Therefore, in this research, we designed two different time divisions: 0:00t∼0:00t+1 and 9:30t∼9:30t+1 to study how tweets and news from the different periods can predict the next-day stock trend. 260,000 tweets and 6,000 news from Service stocks (Amazon, Netflix) and Technology stocks (Apple, Microsoft) were selected to conduct the research. The experimental result shows that opening hours division (9:30t∼9:30t+1) outperformed natural hours division (0:00t∼0:00t+1).

Classifying of VN-Index Bullishness by Bayesian Inference

Decision making in stock market is a movement in which investors gather information and carry out complex analysis to select options, based on market variations and investor's preferences. This involves the facts of risk of return, appreciating or depreciating of stock markets in value and dynamic circumstances. We present a design to study and discover bear and bull markets from macroeconomic variables in a probabilistic manner to assist the decision-making process. Features such as return, risk, simple, and exponential moving average are represented as flexible time series. The learning method that involves conditional dependence of stock variables and inference is described by the base of Bayesian theorem. We highlight our learning method using an actual case study with a consistent stock portfolio optimization. The case study addresses a set of selected stock symbols of VN-index and the logical method is illustrated by significant rates of accuracy over a variation of types of stock symbols.

Effect of public sentiment on stock market movement prediction during the COVID-19 outbreak

Forecasting the stock market is one of the most difficult undertakings in the financial industry due to its complex, volatile, noisy, and nonparametric character. However, as computer science advances, an intelligent model can help investors and analysts minimize investment risk. Public opinion on social media and other online portals is an important factor in stock market predictions. The COVID-19 pandemic stimulates online activities since individuals are compelled to remain at home, bringing about a massive quantity of public opinion and emotion. This research focuses on stock market movement prediction with public sentiments using the long short-term memory network (LSTM) during the COVID-19 flare-up. Here, seven different sentiment analysis tools, VADER, logistic regression, Loughran–McDonald, Henry, TextBlob, Linear SVC, and Stanford, are used for sentiment analysis on web scraped data from four online sources: stock-related articles headlines, tweets, financial news from "Economic Times" and Facebook comments. Predictions are made utilizing both feeling scores and authentic stock information for every one of the 28 opinion measures processed. An accuracy of 98.11% is achieved by using linear SVC to calculate sentiment ratings from Facebook comments. Thereafter, the four estimated sentiment scores from each of the seven instruments are integrated with stock data in a step-by-step fashion to determine the overall influence on the stock market. When all four sentiment scores are paired with stock data, the forecast accuracy for five out of seven tools is at its most noteworthy, with linear SVC computed scores assisting stock data to arrive at its most elevated accuracy of 98.32%.

The financial crash of 2020 and the retail trader’s boon: a correlation between sentiment and technical analysis

The American stock market passed a critical phase during 2020. The CBOE volatility index had spiked from a little over 20 to a little over 50 and returned flat to 16% year on year basis. This paper presents a novel model to measure the engagements of retailer trading through public perception and forced media messages. The markets have proved to be resilient on the expected returns in the long term however the short-term spot markets were unpredictable. Even though the Dow Jones fell from 29,100 points to 19,180 points the big investment banks made huge trading profits. Bank of America's trading revenue grew from $3.8 billion to $5.3 billion whereas the retailers went for the bankrupt companies such as Macy’s and Hertz. The paper discusses the prediction with help of neural networks and NLP models to analyze retailer’s favorite stocks and helps to predict their future expected returns of the stocks. The results of the research create a new key performance index for asset-level risk management using this correlation.

Modeling and Forecasting the Volatility of NIFTY 50 Using GARCH and RNN Models

The stock market is constantly shifting and full of unknowns. In India in 2000, technological advancements led to significant growth in the Indian stock market, introducing online share trading via the internet and computers. Hence, it has become essential to manage risk in the Indian stock market, and volatility plays a critical part in assessing the risks of different stock market elements such as portfolio risk management, derivative pricing, and hedging techniques. As a result, several scholars have lately been interested in forecasting stock market volatility. This study analyzed India VIX (NIFTY 50 volatility index) to identify the behavior of the Indian stock market in terms of volatility and then evaluated the forecasting ability of GARCH- and RNN-based LSTM models using India VIX out of sample data. The results indicated that the NIFTY 50 index’s volatility is asymmetric, and leverage effects are evident in the results of the EGARCH (1, 1) model. Asymmetric GARCH models such as EGARCH (1, 1) and TARCH (1, 1) showed slightly better forecasting accuracy than symmetric GARCH models like GARCH (1, 1). The results also showed that overall GARCH models are slightly better than RNN-based LSTM models in forecasting the volatility of the NIFTY 50 index. Both types of models (GARCH models and RNN based LSTM models) fared equally well in predicting the direction of the NIFTY 50 index volatility. In contrast, GARCH models outperformed the LSTM model in predicting the value of volatility.

An LSTM and GRU based trading strategy adapted to the Moroccan market

Forecasting stock prices is an extremely challenging job considering the high volatility and the number of variables that influence it (political, economical, social, etc.). Predicting the closing price provides useful information and helps the investor make the right decision. The use of deep learning and more precisely of recurrent neural networks (RNNs) in stock market forecasting is an increasingly common practice in the literature. Long Short Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures are among the most widely used types of RNNs, given their suitability for sequential data. In this paper, we propose a trading strategy designed for the Moroccan stock market, based on two deep learning models: LSTM and GRU to predict the closing price in the short and medium term respectively. Decision rules for buying and selling stocks are implemented based on the forecasting given by the two models, then over four 3-year periods, we simulate transactions using these decision rules with different settings for each stock. The returns obtained will be used to estimate an expected return. We only hold stocks that outperform a benchmark index (expected return > threshold). The random search is then used to choose one of the available parameters and the performance of the portfolio built from the selected stocks will be tested over a further period. The repetition of this process with a variation of portfolio size makes it possible to select the best possible combination of stock each with the optimized parameter for the decision rules. The proposed strategy produces very promising results and outperforms the performance of indices used as benchmarks in the local market. Indeed, the annualized return of our strategy proposed during the test period is 27.13%, while it is 0.43% for Moroccan all share Indice (MASI), 15.24% for the distributor sector indices, and 19.94% for the pharmaceutical industry indices. Noted that brokerage fees are estimated and subtracted for each transaction. which makes the performance found even more realistic.

From Comparative and Statistical Assessments of Liveability and Health Conditions of Districts in Hong Kong towards Future City Development

Liveability is an indispensable component in future city planning and is practically linked with the health status of individuals and communities. However, there was nor comprehensive and universal district-level framework for assessing liveability due to geospatial and social discrepancies among different countries. In this study, using Hong Kong, a highly dense and international city as an example, the Liveability and Health Index (LHI-HK) consisting of 30 indicators was established, with 21 of them related to education, economy, housing, walkability/transport, environment, and health facilities aspects, while the health conditions of citizens in individual districts were examined by other 9 indicators. Respective scoring allocation was determined by statistical reasoning, and was applied to quantify the connections between liveability and health among the 18 districts of Hong Kong in both 2016 and 2019. Temporal changes of spatial features could be traced by this quantitative framework, and obvious correlations between liveability and health were attained, with R values of 0.496 and 0.518 in 2016 and 2019, and corresponding slopes of 0.80 and 0.88, respectively. Based on the statistical results, it was found that Sai Kung and Kwun Tong are the most and the least liveable district of Hong Kong in 2019. The LHI-HK index was well-validated by renowned AARP liveability index and The California Healthy Places Index (HPI), with R values of 0.90 and 0.70, and the potential uncertainties due to data projection were less than 2.5% for all districts, which implicates its relevancy and appropriateness in conducting similar spatial assessments in international cities. Further, both favorable and unfavorable spatial arrangements of each of the 3 district types in Hong Kong were identified, namely residential, commercial, and industrial districts. This opens new windows in enhancing liveability and health status within communities, with the aim of promoting the sustainability of cities in the long run.