Performance Forecasting Research Articles

Key considerations in the week-to-week forecasting of individual match actions in football

Short-term forecasting of performance in football is crucial in week-to-week decision making. The current study presented novel contributions regarding the considerations that should be accounted for in the prediction of match actions performed in competitive matches. First, the study examined whether the quantity and recency of training data used to build a prediction model significantly influenced predictive accuracy. Three prediction models were built with the exponential moving weighted average (EMWA) method, each differing in the quantity of training data used (three, five, and seven preceding match days). Next, the study examined if contextual constraints, such as type of match action being predicted, playing position, or player age, significantly influenced predictive accuracy. Match action data from players in the top five European leagues were collected from the 2014/2015 to the 2019/2020 seasons. The model trained using less but more recent data (three preceding match days) demonstrated the greatest accuracy. Next, within the offensive and defensive phases, match actions differed significantly in predictive accuracy. Lastly, significant differences were found in prediction accuracy between playing positions, whereby actions associated with the primary task of the playing position were more accurately predicted. These findings suggest that in the forecasting of individual match actions, practitioners should seek to train the prediction model using more recent data, instead of including as much data as possible. Furthermore, contextual constraints such as the type of action and playing position of the player must be keenly considered.

Halal tourism demand and firm performance forecasting: new evidence from machine learning

ABSTRACT This study forecasts both Halal tourism demand (HTD) and the financial performance of Halal tourism industry of Malaysia using machine learning. Based on the data over the period from 2009 to 2020, this study considered 338,233 tweets sentiments, and 11 Google trend keywords, firm-specific variables, and macroeconomic variables for HTD and financial performance forecasting. Out of 14 machine learning algorithms, this study found Bagged classification and regression trees method outperforms other forecasting models. The forecasting accuracy scores of HTD and firm financial performance models are 93.71% and 80.12%, respectively. The results reveal that internet data variables (Twitter & Google Trend) significantly contribute to the forecasting models. Evidently, our models functioned optimally during the COVID-19 pandemic. This study offers valuable insights for policymakers to devise sustainable Halal tourism.

An adaptive wind power forecasting method based on wind speed-power trend enhancement and ensemble learning strategy

Accurate wind power forecasting (WPF) is essential for power system planning, operation, and management. However, the high uncertainty and stochastic behavior of natural wind brings great challenges to high performance WPF. In this context, an adaptive WPF model based on wind speed-power trend enhancement and an ensemble learning strategy is proposed in this study. For wind speed-power trend enhancement, abnormal data are detected and removed by the combined local outlier factor algorithm and quartile method. The artificial power data are interpolated using a neural network based on the normal wind speed-power distribution. In the ensemble learning strategy, a total of eight individual learners are involved as the candidate base learners. The principle of selecting base learners with low correlation and high accuracy is provided to achieve high performance forecasting, and thus, four base learners with different internal mechanisms are finally selected. The partial least squares regression is utilized for outputs weighting, and the K-fold cross-validation is adopted for dataset division. Collected data from a real wind turbine system are used for performance investigation. Forecasting tests with three time horizons (10, 30, and 60 min) and three seasons (Spring, Summer, and Autumn) are carried out. The results reveal that the proposed model is more accurate and adaptive compared with individual learners and other ensemble models.

Predicting bloc support in Irish general elections 1951–2020: A political history model

ABSTRACT Election forecasting is a growing enterprise. Structural models relying on “fundamental” political and economic variables, principally to predict government performance, are popular in political science. Conventional wisdom though is these standard structural models fall short in predicting individual blocs’ performance and their applicability to multiparty systems is restricted. We challenge this by providing a structural forecast of bloc performance in Ireland, a case primarily overlooked in the election forecasting literature. Our model spurns the economic and performance variables conventionally associated with structural forecasting enterprises and instead concentrates on Ireland’s historical party and governance dynamics in the vein of testing whether these patterns alone offer solid predictions of election outcomes. Using Seemingly Unrelated Regression (SUR), our approach, comprising measures of incumbency, short-term party support, and political and economic shocks, offers reasonable predictions of the vote share performance of four blocs: Ireland's two major parties, Fianna Fáil and Fine Gael, Independents, and the Left bloc combined across 20 elections spanning 60 years.

Advances in Solar PV Systems; A Comprehensive Review of PV Performance, Influencing Factors, and Mitigation Techniques

PV power plants utilizing solar energy to generate electricity on a large scale has become a trend and a new option that has been adopted by many countries; however, in actuality, it is difficult to anticipate how much electricity PV plants will generate. This analysis of existing photovoltaic (PV) power plants provides guidelines for more precise designs and performance forecasting of other upcoming PV technologies. In the literature, some authors have put their efforts into reviewing studies on PV power systems; however, those reviews are too focused on specific aspects of the topic. This study will review, from a broader perspective, recent investigations on PV power systems in the literature that were published between 1990 and 2022. The present study is divided into three main parts. Firstly, a performance assessment review of PV power plants is presented by taking different performance parameters into consideration, which were developed by the “International Electrotechnical Commission (IEC 61724-1)”. These parameters include reference yield, final yield, performance ratio, capacity utilization factor, and system efficiency. Secondly, different identifying factors that were investigated in previous studies, and which affect PV performance, were considered. These factors include solar irradiance, PV technology type, ambient temperature, cell temperature, tilt angle, dust accumulation, and shading effect. Thirdly, different methods were adopted and suggested to counter the effects of these influencing factors to enhance the performance efficiency of the PV power system. A hybrid cooling and cleaning system can use active techniques to boost efficiency during high solar irradiances and ambient temperatures while depending on passive techniques for everyday operations. This comprehensive and critical review identifies the challenges and proposed solutions when using photovoltaic technologies and it will be helpful for researchers, designers, and investors dealing with PV power systems.

Performance forecasts for the primordial gravitational wave detection pipelines for AliCPT-1

AliCPT is the first Chinese cosmic microwave background (CMB) experiment which will make the most precise measurements of the CMB polarization in the northern hemisphere. The key science goal for AliCPT is the detection of primordial gravitational waves (PGWs). It is well known that an epoch of cosmic inflation, in the very early universe, can produce PGWs, which leave an imprint on the CMB in form of odd parity B-mode polarization. In this work, we study the performance of the component separation and parameter estimation pipelines in context of constraining the value of the tensor-to-scalar ratio. Based on the simulated data for one observation season, we compare five different pipelines with different working principles. Three pipelines perform component separation at map or spectra level before estimating r from the cleaned spectra, while the other two pipelines performs a global fit for both foreground parameters and r. We also test different methods to account for the effects of time stream filtering systematics. This work shows that our pipelines provide consistent and robust constraints on the tensor-to-scalar ratio anda consistent sensitivity σ(r) ∼ 0.02. This showcases the potential of precise B-mode polarization measurement with AliCPT-1. AliCPT will provide a powerful opportunity to detect PGWs, which is complementary with various ground-based CMB experiments in the southern hemisphere.

Measuring CMB Spectral Distortions from Antarctica with COSMO: Blackbody Calibrator Design and Performance Forecast

COSMO is a ground-based instrument to measure the spectral distortions (SD) of the Cosmic Microwave Background (CMB). In this paper, we present preliminary results of electromagnetic simulations of its reference blackbody calibrator. HFSS simulations provide a calibrator reflection coefficient of Rsim 10^{-6}, corresponding to an emissivity epsilon =1-R=0.999999. We also provide a forecast for the instrument performance by using an ILC-based simulation. We show that COSMO can extract the isotropic Comptonization parameter (modeled as |y|=1.77 cdot 10^{-6}) as |y|=(1.79pm 0.19)cdot 10^{-6}, in the presence of the main Galactic foreground (thermal dust) and of CMB anisotropies, and assuming perfect atmospheric emission removal.

Prognosticating scientific activity indicators of Russian universities and their rating

Introduction. Organisations’ performance evaluation results have now become an important management resource. Therefore, it is not only compliance with the targets set by the founder that is relevant for the organisation, but also inclusion in the TOP prestigious ratings list, both of general nature and set for a particular activity. The purpose of the research is designing the research performance forecasts for universities and ratings on their basis by simulation modelling methods, as well as the formation of managerial decisions aimed to promote a specific university in the rating list. Materials and methods. The research materials are represented by the data on the number of university staff publications in the leading scientometric databases Web of Science, Scopus, RSCI, and the numbers of academic staff (research and teaching staff) in the period from 2013 to 2021. The methods of mathematical and simulation modelling, as well as the methods of descriptive statistics and comparative analysis of data were used in the research. Results. The dynamics of scientific activity indicators for TOP-50 universities until 2030 was modelled within the framework of studying the methodology for the formation of a specific well-known national rating of Russian universities, on the basis of sixteen universities from the above. The managerial decisions projects allowing a university which is not included in the TOP-50 to get into this list, with regard for minimisation of financial expenses, are proposed by the example of Petrozavodsk State University. It is proposed to implement the said management decision projects through involvement in publication activities of the university academic staff that has not had any annual publications within several preceding years. Following the simulation modelling of projected values of scientific performance indicators, it was revealed that in case of annual increase in the number of publications by 25% on the average, Petrozavodsk State University can essentially improve its positions in the rating of scientific activity and take a position in a range between 40 and 50 by 2025. Discussion and conclusion. The obtained models make it possible to prognosticate not only the total number of articles at particular Russian universities, but also their positions in the rating, both in case of preservation of current tendencies and realisation of different management scenarios. From the practical point of view, the presented results can be useful for the university administration in terms of analysis and management of the scientific work at the university, with the view to improve the academic performance and achieve the set goals.

Impedance-based forecasting of lithium-ion battery performance amid uneven usage

Accurate forecasting of lithium-ion battery performance is essential for easing consumer concerns about the safety and reliability of electric vehicles. Most research on battery health prognostics focuses on the research and development setting where cells are subjected to the same usage patterns. However, in practical operation, there is great variability in use across cells and cycles, thus making forecasting challenging. To address this challenge, here we propose a combination of electrochemical impedance spectroscopy measurements with probabilistic machine learning methods. Making use of a dataset of 88 commercial lithium-ion coin cells generated via multistage charging and discharging (with currents randomly changed between cycles), we show that future discharge capacities can be predicted with calibrated uncertainties, given the future cycling protocol and a single electrochemical impedance spectroscopy measurement made immediately before charging, and without any knowledge of usage history. The results are robust to cell manufacturer, the distribution of cycling protocols, and temperature. The research outcome also suggests that battery health is better quantified by a multidimensional vector rather than a scalar state of health.

Fractal Theory and Its Financial Applications for Improving the Quality of Professional Training at The Higher School of Economics

The article presents the didactic potential of modern fractal theory and its financial applications related to modeling and forecasting of financial performance. The purpose of the study is to identify the main content and methodological features of the disclosure of fractal theory and its financial applications in the practice of professional training of students of economic universities. The results of the analysis of popular science and scientific literature on fractal theory and its applications allowed us to clarify its didactic potential in the system of higher economic education. The use of elements of the technological approach at the Higher School of Economics made it possible to construct the educational process on fractal theory and its financial applications in the form of a system of micro-goals of the basic level, which serves as a guideline for organizing and planning the results of educational and cognitive activity of students of the Bachelor of Economics. Involvement of various techniques and methods of the theory of pedagogical technologies based on the establishment and study of the laws of the educational process as the results of scientific knowledge of the process of human education, as well as financial faculties of the Plekhanov Russian University of Economics and the Financial University under the Government of the Russian Federation as the basis of experimental work allowed to identify the attitude of students to fractal theory and its applications, to conduct primary testing of fractal theory as a new element of the content of mathematical training, as well as directions for improving the educational process in applied mathematical disciplines. Special attention is paid to the mechanisms of development of students’ competencies in the field of decision-making in conditions of risk and uncertainty, a meaningful choice of methods for studying financial situations that require optimal decisions. A system of micro-goals of the basic level is presented, consisting of thirteen micro-goals and allowing a teacher of mathematical disciplines to design invariant content in the field of fractal theory and its applications for higher economic school. Attention is also focused on the need to update the methodological work of teachers of mathematical disciplines on the design and construction of the educational process. Including the base level set by the system of micro-goals presented in this article, which regulates the educational process in the language of educational and cognitive activity of a student of an economic bachelor’s degree. It is noted that the complex transformations taking place in modern society affect various aspects of social, financial and economic relations, increase the requirements for the methodological, design and technological culture of a teacher of mathematical disciplines. The prospects of the study include the development of criteria for the selection of digital tools to support fractal theory and its financial applications as an element of the content of professional training, as well as the development and subsequent implementation of a program of additional professional education on alternative approaches to decision-making in the financial sector. The content of the article can be useful for the implementation of applied, professional strengthening of the teaching of compulsory mathematical disciplines for students studying in the direction of “Economics” of various directions (Mathematical methods in economics, World Economy, Finance and Credit, etc.), and for the formulation of new academic disciplines of students’ choice, as well as improving the content of programs of additional professional education related to the quantitative justification of decisions.

Impedance-Based Li-Ion Battery Forecasting amid Uneven Usage

Accurate forecasting of Li-ion battery performance is important for easing consumer concerns about the safety and reliability of electric vehicles. Most research on battery health prognostics focuses on the R&D setting where cells are subjected to the same usage patterns, yet in practice there is great variability in use across cells and cycles, making forecasting much more challenging.In my talk, I will show that a combination of battery `biomarkers’ derived from electrochemical impedance signals with probabilistic machine learning enables us to accurately forecast future battery performance amid uneven usage, even when cell history is completely unknown. More broadly, our results bring into question the concept of a scalar State of Health, and instead suggest that battery state is better quantified by a multidimensional vector. I will discuss how this insight lays the foundations for novel algorithms for battery prognostics and control. I will further outline our application of such algorithms in optimal protocol design for intelligent battery charging, and low-data inference via transfer learning across cell chemistries and usage patterns.

Recurrent Neural Networks for Pavement Performance Forecasting: Review and Model Performance Comparison

Accurate pavement performance forecasting is critical in supporting transportation agencies’ predictive maintenance strategies: programs that prolong pavement service life while using fewer resources. However, because of the complex nature of pavement deterioration, high accuracy for long-term and project-level pavement performance forecasting is challenging to traditional models. Therefore, researchers have taken advantage of machine learning (ML) technology to create more sophisticated models in recent years. However, there are no extant studies that compare different ML models on a singular, real-world, large-scale, and comprehensive pavement data set to evaluate their capability for pavement performance forecasting. Thus, the goal of this study is to critically evaluate ML models, such as multiple linear regression (MLR), fully connected neural network (FCNN), recurrent neural network (RNN), gated recurrent unit (GRU), long short-term memory (LSTM), and a hybrid LSTM-FCNN model, on Florida’s statewide, 31 year historical pavement data set. The results demonstrate that the RNN, GRU, LSTM, and LSTM-FCNN models perform significantly better than MLR and FCNN for predicting time-series pavement condition, with the LSTM-FCNN model performing the best. This result provides a valuable demonstration and recommendation to transportation agencies and researchers that RNN-based ML models are a promising direction to improve the accuracy of pavement performance forecasting.

Time-evolution and forecasting of environmental and energy performance of electricity production system at national and at bidding zone level

The electricity generation system has faced exceptional change lately because of several aspects: the electrification of heating and transport sectors, the spread of distributed energy generation, and the increase of renewable share in the electricity production mix. All these factors have contributed to exacerbate the variability of power system operation. This work aims to present hourly data analysis of the electricity production (from fossil fuels and renewables) at the country level (Italy) and at the bidding zone level in the period 2015–2019. Based on different time-resolution, several datasets have been examined and a reproducible method has been defined to overcome the temporal resolution misalignment. Subsequently, the data has been used to define and calculate the time-dependent energy efficiency and environmental indicators for the electricity system with an hourly timestep both for Italy and related bidding zones. The results have demonstrated that these parameters are extremely variable year by year and hour by hour both at the national and bidding zones level. For example, one of the analysed energy efficiency indicators referred to Italy ranges from 0.4 in the hours in which the renewable share is lower than 10% to 1.8 when the renewable share reaches 80%. At the bidding zone level, the electric efficiency indicators, and carbon dioxide emission factor for electricity show a pattern depending on the specific electricity production mix in each zone evidencing a great difference compared to outcomes related to the whole of Italy. The findings of this work evidence the need of accurate knowledge of these operational indexes in the evaluation of electric-driven energy conversion systems performance, energy planning, and in the improvements of electricity market efficiency.

A Comparative Analysis of Solar PV Forecast using SVM under CO2 Concentration

Installation of a solar PV plant requires an understanding of the performance of solar PV panels in various weather conditions by which solar output power has to be predicted well in advance. Solar PV technology is the most reliable and cost-effective technology compared to other renewable energy technologies. To minimize the cost of production and pollution, it is very essential to improve the techno-economic parameters of the technology and have a better understanding of the development of solar PV technology but the efficiency of solar PV technology depends on various environmental factors. Irradiation and temperature are the main inputs in solar PV technology. Again both the terms depend on greenhouse content and its concentration in the atmosphere. Due to the influence of many factors, the forecasting of the solar PV performance in terms of output is a difficult task. So various comparative analysis has been used for forecasting solar PV power. This paper has analysed support vector machines through the MATLAB simulation model for forecasting the performance parameters of the solar PV system. An experiment has been conducted at NRRI, Cuttack in collecting real-time data for analysis.

Strategies for data analytics projects in business performance forecasting: a field study

Data analytics is applied in various fields, including business performance forecasting, but companies struggle with its implementation. Following a cross-sectional field study approach, we make two contributions. First, we elaborate on the central role played by the head controller in generating trust in analytics solutions and thus, making the project successful. Second, we identify three patterns in the way companies plan, implement, and then use data analytics in the context of business performance forecasting. The two successful patterns are the ones that start with a limited but tangible objective (either in term of information precision, or rapidity of processing) that can be expended in a second time.

Anti-Poverty Performance Assessment and Forecasting

In order to further help each unit that mitigates the poverty of impoverished regions to improve the efficiency of poverty alleviation, this paper establishes a poverty alleviation performance evaluation index system. Firstly, we analyze the correlation among poverty alleviation indicators through a matrix density diagram. Second, the questions are divided into target layer (poverty alleviation performance), criterion layer (poverty alleviation efficiency, poverty alleviation effect, and poverty alleviation rate), and indicator layer, and the fuzzy hierarchical integrated evaluation method is used to calculate the performance score of each poverty alleviation unit. In addition, based on the historical data, support vector machines were used to calculate the grading rules and predict whether the village could be awarded the title of "advanced village in poverty alleviation". Finally, based on the study, recommendations were made to the National Poverty Alleviation Office for the differences in the individuality of the villages and the distribution of the work content of the poverty alleviation units.

PFCMVO: Political fractional competitive multi-verse optimization enabled deep neuro fuzzy network for student performance estimation in spark environment

Student performance calculation is an essential process in online learning scheme, which intends to afford students along with admittance to active learning. Student performance forecast is most concerning problem in education and training field, particularly in educational data mining (EDM). The prediction process provisions the students to choose courses and intend suitable training strategies for themselves. Furthermore, student performance calculation permits lecturers and educational supervisors to designate which students should be observed and maintained to finish their plans with finest outcomes. These provisions can decrease the official notices and exclusions from universities because of students’ poor performance. In this paper, Political Fractional Competitive Multi-verse Optimization enabled Deep Neuro fuzzy network (PFCMVO enabled DNFN) uses spark framework for student performance calculation. Moreover, Yeo–Johnson transformation is applied for transforming the input data for effectual student performance prediction. In addition, Damerau–Levenshtein (DL) distance is applied to select appropriate features. The DNFN classifier is utilized to execute student performance prediction where the classifier is trained by PFCMVO algorithm. The developed student performance prediction model outperforms than the other existing techniques with respect to Precision, Recall, [Formula: see text]-measure, and Prediction accuracy of 0.9259, 0.9321, 0.9290, and 0.9372 for dataset-1 and 0.9126, 0.9271, 0.9198, and 0.9248 for dataset-2, respectively.

The Comparison of The Islamic and Conventional Bank Performance before and During Covid-19 Pandemic in Indonesia

This study aims to determine and compare the financial stability of banks during the crisis which is still being debated by taking the period before and after the covid 19 pandemics. This study uses a sample of all transactions of conventional banks and Islamic banks throughout Indonesia that are recorded by the Indonesian financial services authority. With a population of all conventional financial institutions and Islamic financial institutions, both registered and unregistered by Indonesian financial services authorities throughout Indonesia. The type of data in this study is secondary data sourced from the Indonesian financial services authority. To find out and compare the performance of conventional banks with Islamic banks and the resilience of conventional banks and Islamic banks to shocks, an analysis of the financial behavior of data in commercial banks was carried out using Threshold Autoregressive. We find that Islamic banks tend to be more stable in facing financial challenges due to the COVID-19 pandemic compared to conventional banks. The performance of conventional banks was very good in the period before the COVID-19 pandemic. However, when the coronavirus pandemic began to be reported, there was a huge decline in performance. Conventional bank recovery efforts have not been able to return to the original track. Conventional bank performance is slowing down and it tends to be difficult to return to its original performance value (before the COVID-19 outbreak). However, from the graph of performance forecasting between Islamic Commercial Banks and Conventional Banks, it can be seen that there is a difference in performance stability between Islamic Commercial Banks and Conventional Banks facing the COVID-19 pandemic.

ANN modeling for forecasting of VCR engine performance and emission parameters fuelled with green diesel extracted from waste biomass resources.

In this research work, the experimental tests were conducted on a single-cylinder, constant speed, variable compression ratio (VCR) engine fuelled with green diesel. Initially, bio-oil was extracted from waste Trichosanthes cucumerina fruit seeds using the Soxhlet apparatus. The acquired bio-oil is used to make green diesel through the trans-esterification process. The fuel blends were prepared with different proportions of Trichosanthes cucumerina biodiesel (TCB) in diesel fuel (30%, 50%, and 70%) for the experimental test, and their thermo-physical properties were evaluated according to ASTM standards. At full load condition, the TCB30 blend with CR 18:1 gives closer engine performance of brake thermal efficiency (33.52%), brake specific fuel consumption (0.27kg/kWh), and exhaust gas temperature (389.56°C) and reduced emission levels of unburned hydrocarbon by 13.51%, carbon monoxide by 10.82%, smoke opacity by 16.87%, and the penalty of nitric oxide by 17.56% equated with neat diesel fuel. The engine performance and emission parameters are predicted using multiple regression artificial neural network (ANN) models. A database generated from the experimental results is used to train the ANN model. The average correlation coefficient (R) of the trained ANN model is 0.99673, which is closer to 1. It indicates that the proposed ANN model can generate the exact correlation between input factors and output responses. As a result, the application of ANN is a better forecasting tool for predicting VCR engine performance and emission characteristics.

Building-Integrated Photovoltaic (BIPV) products and systems: A review of energy-related behavior

This paper reviews the main energy-related features of building-integrated photovoltaic (BIPV) modules and systems, to serve as a reference for researchers, architects, BIPV manufacturers, and BIPV designers. The energy-related behavior of BIPV modules includes thermal, solar, optical and electrical aspects. Suitable standardization to evaluate heat transfer and solar heat gain by BIPV modules still need to be developed further since BIPV elements behave differently to the building elements they substitute. The optical properties of BIPV modules, such as light transmittance or color rendering, also play a role in the search for a good balance between energy saving, electricity generation, aesthetics and visual comfort. However, architecturally adapted BIPV design may affect the electrical performance also, by reducing the efficiency of BIPV modules and systems compared to standard photovoltaic (PV) ones. This is not the sole challenge for the electrical designers, as the special operating conditions of BIPV systems such as non-homogeneous irradiance complicate the electrical design and the forecasting of BIPV performance. The aim of this review is to present the current state of knowledge of the aspects mentioned above, to promote continued progress in BIPV and to inform suitable standardization efforts.