Review of modern models and methods of analysis of time series of dynamics of processes in social, economic and socio-technical systems

Andrianova, Elena; Golovin, S. A.; Зыков, С. В.; Lesko, S. A.; Чукалина, Е. Р.

doi:10.32362/2500-316x-2020-8-4-7-45

Cited by 25 publications

(13 citation statements)

References 40 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The insignificant terms have been removed from the model. The expression (2) shows the result of this process:…”

Section: Resultsmentioning

confidence: 99%

“…In this research there are four datasets that have been under investigation. The Students' Performance dataset 1,2,3 has got two parts including grades at math and Portuguese language exams. There are values of social and behavioral features of each student.…”

Section: Introductionmentioning

confidence: 99%

“…Dependencies between traditional grades and emodji-based reactions on messages in e-learning system can confirm that elearning process leads to gaining knowledge by students in the way they like or it can show that 1 Student Grade Prediction. URL: https://www.kaggle.com/ dipam7/student-grade-prediction 2 Student Performance Data Set. URL: https://www.kaggle.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

The impact of e-learning and social parameters on students’ academic performance

Petrusevich¹

2020

Science for Education Today

View full text Add to dashboard Cite

Introduction. The article examines the problem of assessing students' academic performance in the current situation. The purpose of the paper is to evaluate the influence of e-learning and some social and behavioral parameters on students’ academic performance. Materials and Methods. The author employed the machine learning procedures in order to identify and assess the current problems of the educational system, students’ behavior, and universities’ policy. Methods of mathematical analysis and statistics as well as ensemble methods (gradient boosting and the random forest algorithms) were used in order to achieve high accuracy of the research. Results. The author conducted the analysis of the following datasets devoted to academic performance at higher and secondary educational institutions in a number of countries: Students’ Performance in Portugal, E-learning Student Reactions and Students’ Academic Performance. The purposes of the current study were to identify statistical correlations between social parameters of students and the level of their academic performance and to understand how academic performance is determined by the implementation of online learning and blended learning. The research findings suggest that mathematical statistics and data analysis methods allow to identify correlations between students’ performance data and reveal hidden relationships which can be important for university staff. Conclusions. In conclusion, the author summarizes the results of evaluating the impact of the introduction of e-learning elements and some social parameters on students’ academic performance. Keywords Clustering students; Blended learning; Academic performance evaluation; Digitalization of education; Digital technologies in education; Correlation of features; performance improvement.

show abstract

“…The insignificant terms have been removed from the model. The expression (2) shows the result of this process:…”

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

The impact of e-learning and social parameters on students’ academic performance

Petrusevich¹

2020

Science for Education Today

View full text Add to dashboard Cite

show abstract

“…A group of scientists [13] described the directions of promising research in the field of analysis and modeling of the dynamics of time series of processes in complex systems with the presence of a human factor. General information about time series and tasks of their analysis is given.…”

Section: Literature Reviewmentioning

confidence: 99%

The concept of assessing the City Council management control level for effective decision making

Melikhova

Mikhailutsa

2021

SHS Web Conf.

View full text Add to dashboard Cite

In present paper, time series models of revenues and expenses of general and special local budget fund in Zaporizhzhia City Council for 2017-2020 are built. The possibility of forecasting time series has been investigated on the example of local budget revenues and expenses. The concept of assessing the level of management control which consists of information-analytical circuit, analysis and modeling circuit, and decision-making circuit has been proposed. The best options for absolute and comparative economic efficiency of accounting and economic expenses of management control have been substantiated. The forecast for calculating the absolute and comparative economic efficiency of management control on the data of Zaporizhzhia City Council is shown and the annual economic effect from its implementation is calculated. The methodological approaches to the analysis of income and expenses of the general and special fund have been improved. They, unlike existing methods, include time series modeling and studies describing complex changes in parameters over time. This made it possible to carry out high-quality management control and increase the efficiency of activities. The SPSS Statistics data analysis package is used for data processing, test assumption and building the future strategy.

show abstract

“…Time series modeling is usually based on information criteria evaluation (Bayes or Akaike criteria) in order to choose the best model for investigated time series [1][2][3]. In practice often a few models have got good criteria values and it's difficult to choose the best one.…”

Section: Introductionmentioning

confidence: 99%

Improvement of time series forecasting quality by means of multiple models prediction averaging

2021

Proceedings of the III International Workshop on Modeling, Information Processing and Computing (MIP: Computing-2021)

View full text Add to dashboard Cite

Construction of time series models is usually based on Akaike and Bayes information criteria. Requirement of model simplicity is built inside the information criteria structure and the best fitted models aren't always best in terms of criteria values. Often there are a few best models that fit investigated time series well and there's problem of choice between them. Usually information criteria values allow to choose among them. But if one needs the best model by forecasts quality, best fitted models, or there are other thoughts a research has to choose and test models manually. At the same time when a few models are chosen it's possible to construct their combination. The simplest way is to count mean value of their forecasts and to use it as a combined prediction. Practical researches confirm that forecast error gets lower in this approach. Also, more complex construction than averaging of forecasts can be used (for example, weighted voting that is widely used in bagging technique in solution of classification problems). But this approach hasn't got enough theoretical base. From theoretical point of view confidence intervals of time series forecasts (usually here they're considered as prediction intervals) is also very complex task. Intervals tend to be very wide even for models with good prediction quality in terms of mean forecast errors. Thus, prediction intervals are rare in use. In this paper a few time series models are constructed for wage and income indices of Russian macroeconomic time series. Their predictions are combined into one forecast and it's quality is compared to individual ones. Transformation of forecast variance and prediction intervals in case of simple (moving averages MA(q) and autoregressions AR(p) of low order) models is also considered but is a part of further work.

show abstract

Review of modern models and methods of analysis of time series of dynamics of processes in social, economic and socio-technical systems

Cited by 25 publications

References 40 publications

The impact of e-learning and social parameters on students’ academic performance

The impact of e-learning and social parameters on students’ academic performance

The concept of assessing the City Council management control level for effective decision making

Improvement of time series forecasting quality by means of multiple models prediction averaging

Contact Info

Product

Resources

About