Stock Price Prediction using Machine Learning Algorithms

Machine learning has broad applications in the finance industry. Risk Analytics, Consumer Analytics, Fraud Detection, and Stock Market Predictions are some of the domains where machine learning methods can be implemented. Accurate prediction of stock market returns is extremely difficult due to volatility in the market. The main factor in predicting a stock market is a high level of accuracy and precision. With the introduction of artificial intelligence and high computational capacity, efficiency has increased. In the past few decades, the highly theoretical and speculative nature of the stock market has been examined by capturing and using repetitive patterns. Various machine learning algorithms like Multiple Linear Regression, Polynomial Regression, etc. are used here. The financial data contains factors like Date, Volume, Open, High, Low Close, and Adj Close prices. The models are evaluated using standard strategic indicators RMSE and R2 score. Lower values of these two indicators mean higher efficiency of the trained models. Various companies employ different types of analysis tools for forecasting and the primary aim is the accuracy to obtain the maximum profit. The successful prediction of the stock will be an invaluable asset for the stock market institutions and will provide real-life solutions to the problems of the investors. Keywords: Stock prices, Analysis, Accuracy, Prediction, Machine Learning, Regression, Finance

Fingerprint Database Enhancement by Applying Interpolation and Regression Techniques for IoT-based Indoor Localization

Most applied indoor localization is based on distance and fingerprint techniques. The distance-based technique converts specific parameters to a distance, while the fingerprint technique stores parameters as the fingerprint database. The widely used Internet of Things (IoT) technologies, e.g., Wi-Fi and ZigBee, provide the localization parameters, i.e., received signal strength indicator (RSSI). The fingerprint technique advantages over the distance-based method as it straightforwardly uses the parameter and has better accuracy. However, the burden in database reconstruction in terms of complexity and cost is the disadvantage of this technique. Some solutions, i.e., interpolation, image-based method, machine learning (ML)-based, have been proposed to enhance the fingerprint methods. The limitations are complex and evaluated only in a single environment or simulation. This paper proposes applying classical interpolation and regression to create the synthetic fingerprint database using only a relatively sparse RSSI dataset. We use bilinear and polynomial interpolation and polynomial regression techniques to create the synthetic database and apply our methods to the 2D and 3D environments. We obtain an accuracy improvement of 0.2m for 2D and 0.13m for 3D by applying the synthetic database. Adding the synthetic database can tackle the sparsity issues, and the offline fingerprint database construction will be less burden. Doi: 10.28991/esj-2021-SP1-012 Full Text: PDF

How AI chatbots have reshaped the frontline interface in China: examining the role of sales–service ambidexterity and the personalization–privacy paradox

PurposeThis study serves two purposes: (1) to evaluate the effects of organizational ambidexterity by examining how the balanced and the combined sales–service configurations of chatbots differ in their abilities to enhance customer experience and patronage and (2) to apply information boundary theory to assess the contingent role that chatbot sales–service ambidexterity can play in adapting to customers' personalization–privacy paradox.Design/methodology/approachAn online survey of artificial intelligence chatbots users was conducted, and a mixed-methods research design involving response surface analysis and polynomial regression was adopted to address the research aim.FindingsThe results of polynomial regressions on survey data from 507 online customers indicated that as the benefits of personalization decreased and the risk to privacy increased, the inherently negative (positive) effects of imbalanced (combined) chatbots' sales–service ambidexterity had an increasing (decreasing) influence on customer experience. Furthermore, customer experience fully mediated the association of chatbots' sales–service ambidexterity with customer patronage.Originality/valueFirst, this study enriches the literature on frontline ambidexterity and extends it to the setting of human–machine interaction. Second, the study contributes to the literature on the personalization–privacy paradox by demonstrating the importance of frontline ambidexterity for adapting to customer concerns. Third, the study examines the conduit between artificial intelligence (AI) chatbots' ambidexterity and sales performance, thereby helping to reconcile the previously inconsistent evidence regarding this relationship.

Analysis and Prediction Model of Fuel Consumption and Carbon Dioxide Emissions of Light-Duty Vehicles

Due to the alarming rate of climate change, fuel consumption and emission estimates are critical in determining the effects of materials and stringent emission control strategies. In this research, an analytical and predictive study has been conducted using the Government of Canada dataset, containing 4973 light-duty vehicles observed from 2017 to 2021, delivering a comparative view of different brands and vehicle models by their fuel consumption and carbon dioxide emissions. Based on the findings of the statistical data analysis, this study makes evidence-based recommendations to both vehicle users and producers to reduce their environmental impacts. Additionally, Convolutional Neural Networks (CNN) and various regression models have been built to estimate fuel consumption and carbon dioxide emissions for future vehicle designs. This study reveals that the Univariate Polynomial Regression model is the best model for predictions from one vehicle feature input, with up to 98.6% accuracy. Multiple Linear Regression and Multivariate Polynomial Regression are good models for predictions from multiple vehicle feature inputs, with approximately 75% accuracy. Convolutional Neural Network is also a promising method for prediction because of its stable and high accuracy of around 70%. The results contribute to the quantifying process of energy cost and air pollution caused by transportation, followed by proposing relevant recommendations for both vehicle users and producers. Future research should aim towards developing higher performance models and larger datasets for building APIs and applications.

Combined Surfactant and Enzyme-Assisted Extraction of Pectin from Hawthorn (Crataegus monogyna Jacq.) Fruits

Introduction. Commercial pectin is usually obtained from apples or citrus fruits. However, some wild fruits, such as hawthorn, are also rich in pectin with valuable nutritional and medical properties. The research objective was to study and improve the process of combined surfactant and enzyme-assisted extraction of pectin from hawthorn fruits. Study objects and methods. The study involved a 1% solution of Polysorbate-20 surfactant and a mix of two enzymes, namely cellulase and xylanase, in a ratio of 4:1. The response surface methodology with the Box-Behnken experimental design improved the extraction parameters. The experiment featured three independent variables – temperature, time, and solvent-to-material ratio. They varied at three levels: 20, 40, and 60°C; 120, 180, and 240 min; 15, 30, and 45 mL per g. Their effect on the parameters on the pectin yield was assessed using a quadratic mathematical model based on a second order polynomial equation. Results and discussion. The response surface methodology made it possible to derive a second order polynomial regression equation that illustrated the effect of extraction parameters on the yield of polyphenols. The regression coefficient (R2 = 98.14%) and the lack-of-fit test (P > 0.05) showed a good accuracy of the model. The optimal extraction conditions were found as follows: temperature = 41°C, time = 160 min, solvent-to-material ratio = 32 mL per 1 g. Under the optimal conditions, the predicted pectin yield was 14.9%, while the experimental yield was 15.2 ± 0.4%. The content of galacturonic acid in the obtained pectin was 58.5%, while the degree of esterification was 51.5%. The hawthorn pectin demonstrated a good complex-building ability in relation to ions of copper (564 mg Cu2+/g), lead (254 mg Pb2+/g), and cobalt (120 mg Co2+/g). Conclusion. Combined surfactant and enzyme-assisted extraction made improved the extraction of pectin from hawthorn fruits. The hawthorn pectin can be used to develop new functional products.

Individual Creativity in Digital Transformation Enterprises: Knowledge and Ability, Which Is More Important?

Digital technological innovation is reshaping the pattern of industrial development. Due to the shortage of digital talents and the frequent mobility of these people, the competition for talents will be very fierce for organizations to realize digital transformation. The digitization transformation of China’s service industry is far ahead of that of industry and agriculture. It is of great significance to study the organizational management and talent management of service enterprises to reduce the negative impact of insufficient talent reserve and meet the needs of digital development. Based on 378 valid questionnaires from China’s service industry, this paper applied polynomial regression and a response surface model to analyze the impact of two kinds of person-environment fit on work engagement and individual creativity. The results show that: (1) under the combination of high morality and high talent, work engagement and individual creativity are the highest; (2) individual creativity is stronger under the condition of high morality and low talent than under low morality and high talent; and (3) work engagement mediates the influence of morality and talent on individual creativity. The research reveals the internal mechanism by which morality and talent cooperatively promote individual creativity, which provides theoretical guidance for management practice of service firms to improve individual creativity in the process of digital transformation.

Study on optimal adsorption conditions of norfloxacin in water based on response surface methodology

The waste pomelo peel was pyrolyzed at 400 °C to prepare biochar and used as adsorbent to remove norfloxacin (NOR) from simulated wastewater. The adsorption conditions of norfloxacin by biochar were optimized by response surface methodology (RSM). On the basis of single-factor experiment, the adsorption conditions of biochar dosage, solution pH and reaction temperature were optimized by Box-Behnken Design (BBD), and the quadratic polynomial regression model of response value Y1 (NOR removal efficiency) and Y2 (NOR adsorption capacity) were obtained respectively. The results show that the two models are reasonable and reliable. The influence of single factor was as follows: solution pH > biochar dosage > reaction temperature. The interaction between biochar dosage and solution pH was very significant. The optimal adsorption conditions after optimization were as follows: biochar dosage = 0.5 g/L, solution pH = 3, and reaction temperature = 45 °C. The Y1 and Y2 obtained in the verification experiment were 75.68% and 3.0272 mg/g, respectively, which were only 2.38% and 0.0242 mg/g different from the theoretical predicted values of the model. Therefore, the theoretical model constructed by response surface methodology can be used to optimize the adsorption conditions of norfloxacin in water.

PROCESSING SUNSHINE DURATION MEASUREMENTS FOR THE ASSESSMENT OF SOLAR RADIATION IN CLIMATIC REGIONS OF THE CENTRAL AFRICAN REPUBLIC

The objectives of this work carried out in the Central African Republic are to propose new correlations between the components of solar radiation and the sunshine duration on a horizontal surface on the ground, and then to make an evaluation of the solar potential in the cities of Bambari, Birao and Bangui. Polynomial regression models were used and their parameters were estimated by the ordinary least squares method. A statistical evaluation allowed us to compare the performance of the models. The best correlations are then used to estimate the global and diffuse radiation. In the city of Birao, the estimated global radiation is around 6 kWh/m2.j and the diffuse radiation around 2 kWh/m2.j ; in Bambari the global radiation is around 5.4 kWh/m2.j and the diffuse around 2.3 kWh/m2.j ; in Bangui the global radiation is around 5 kWh/m2.j and the diffuse radiation around 2.3 kWh/m2.j. The potential solar in all these regions is very favorable for small and large-scale solar photovoltaic applications.

Persistently high hepatitis C rates in haemodialysis patients in Brazil [a systematic review and meta-analysis]

We conducted a systematic review and meta-analysis of studies assessing HCV infection rates in haemodialysis patients in Brazil (Prospero CRD #42021275068). We included studies on patients under haemodialysis, comprising both convenience samples and exhaustive information from selected services. Patients underwent HCV serological testing with or without confirmation by HCV RNA PCR. Exclusion criteria were the following: absence of primary empirical information and studies without information on their respective settings, study year, accurate infection rates, or full specification of diagnostic tests. Studies with samples ≤ 30 and serial assessments with repeated information were also excluded. Reference databases included PubMed, LILACS, Scopus, and Web of Science for the period 1989–2019. A systematic review was carried out, followed by two independent meta-analyses: (i) studies with data on HCV prevalence and (ii) studies with a confirmatory PCR (i.e., active infection), respectively. A comprehensive set of different methods and procedures were used: forest plots and respective statistics, polynomial regression, meta-regression, subgroup influence, quality assessment, and trim-and-fill analysis. 29 studies and 11,290 individuals were assessed. The average time patients were in haemodialysis varied from 23.5 to 56.3 months. Prevalence of HCV infection was highly heterogeneous, with a pronounced decrease from 1992 to 2001, followed by a plateau and a slight decrease in recent years. The summary measure for HCV prevalence was 34% (95% CI 26–43%) for studies implemented before 2001. For studies implemented after 2001, the corresponding summary measure was 11% (95% CI 8–15%). Estimates for prevalence of active HCV infection were also highly heterogeneous. There was a marked decline from 1996 to 2001, followed by a plateau and a slight increase after 2010. The summary measure for active HCV infection was 19% (95% CI 15–25%) in studies carried out before 2001. For studies implemented after 2001, the corresponding summary measure was 9% (95% CI 6–13%). Heterogeneity was pervasive, but different analyses helped to identify its underlying sources. Besides the year each study was conducted, the findings differed markedly between geographic regions and were heavily influenced by the size of the studies and publication biases. Our systematic review and meta-analysis documented a substantial decline in HCV prevalence among Brazilian haemodialysis patients from 1992 to 2015. CKD should be targeted with specific interventions to prevent HCV infection, and if prevention fails, prompt diagnosis and treatment. Although the goal of HCV elimination by 2030 in Brazil remains elusive, it is necessary to adopt measures to achieve micro-elimination and to launch initiatives towards targeted interventions to curb the spread of HCV in people with CKD, among other high-risk groups. This is of particular concern in the context of a protracted COVID-19 pandemic and a major economic and political crisis.

Development and Testing of a Modular Sunlight Transport System Employing Free-Form Mirrors

The energy consumption of artificial lighting and its impacts on health have stimulated research into natural lighting systems. However, natural lighting system designs are mainly custom, making them costly and difficult to replicate. This study took an office space as a testing field in order to develop a highly adaptable and adjustable modular natural light illumination system. We divided the system into multiple module designs, demonstrated the use of simple development and fabrication processes and integrated a freeform reflector into the system. In creating a freeform mirror, the optical simulation results of the tested field were regressed (through polynomial regression) to achieve a uniformly illuminated plane, and a high-efficiency light-emitting system was produced. Finally, an active heliostat was used to collect sunlight, combined with actual manufacturing verification and measurement results, in order to create an excellent indoor lighting system. As a result, we presented a low-cost and easy-to-design natural light illumination system for the assisted lighting of office areas.