Forecast Values Research Articles

Relative Risk (RR) Analysis and Prediction as Part of Assessing Occupational Safety and Determining Priorities for Action in Occupational Health and Safety in the Construction Industry in Poland

Risks are associated with every human activity. Accidental events are recorded in enterprises in the construction industry every day. Those events differ among themselves in the severity of consequences and the number of victims. It is important to reduce them effectively based on the conclusions of accident rate analyses. The study outlines the process of relative risk (RR) analysis and carries out a process of quantitative data prediction to determine priorities for action in the area of accident risk reduction. For the construction industry, being the subject of the analyses, statistical data on the number of persons injured in accidents at work in 2006–2021 were compiled, the relative risk (RR) was determined, and a prediction process using the Brown model and Winters’ model was performed. The relative risk analyses allowed for determining priorities for action in occupational health and safety. Based on the analyses, it was concluded that it is possible to adapt econometric models in the area of relative risk prediction, and the obtained forecast values may be the basis for taking actions regarding occupational health and safety.

Forecasting the GDP in the United States by Using ARIMA Model

This paper aims to give an overall view of the Gross Domestic Product (GDP) in the United States and determine the optimal model to predict the growth of GDP by using the Autoregressive Integrated Moving Average Model (ARIMA). The ARIMA model was performed for 93 years from 1929 to 2022 of Gross Domestic Product, Billions of Dollars, Annually from Federal Reserve Economic Data (https://fred. stlouisfed.org). The researcher conclude that the estimated model of the first-order difference for the logarithm of GDP (DLGDP) series is ARIMA (1,1,1) with coefficients: C = 0.057064, AR (1) = 0.489046 & MA (1) = 0.265583 where S.E. of regression equals 0.051529, R-squared value is about 0.412974, Durbin-Waston statistic (1.961008) and the probability of F-statistic equals (0.000000), which gives the forecast value 0.10436 of LGDP in 2022, while the actual value equals 0.8818 with very low relative error 1.617%, therefore, the forecast value is close to the actual value and indicates that the ARIMA (1,1,1) model has a good fitting effect.

Application of the Average Based Fuzzy Time Series Model in Predictions Seeing the Use of Travo Substations

PT PLN expects the delivery of information quickly in predicting the capacity of transformer substations in each region in view of population growth in industrial areas. Unbalanced and overloaded electricity that is not suitable for the capacity of the transformer substation so that the results of this study are more optimal in predicting the usage load at the transformer substation using the methodaverage based fuzzy time series. The application of this method can provide fast and accurate information in accordance with consumer expectations in predicting each need in each area and the number of managed substations. The capacity of the substation can be seen in 1 phase and 3 phase with the percentage of loading quickly and precisely with the current transformer card system. The purpose of the transformer distribution in this study is to look at reducing high voltage to low voltage, so that the voltage used is in accordance with the customer's electrical equipment rating or the load rating used by all consumers in each region. The research methodology is to determine the placement of distribution transformer locations that are not suitable which can affect the end voltage drop on consumers or the drop/drop in consumer line end voltage and view complete data from the specifications of the distribution transformers along with the locations of distribution transformers that can be managed through Development of a mobile device-based Distribution Transformer Recording System at PT PLN. The results of this study in transformer power 100 consumption 99.43, unbalanced 28%, fuzzification A8, FLRG G8, forecasting results 10.69 with a Mape forecast value of 0.57%. Furthermore, power consumption of transformer 50 is 36.70, unbalanced 78%, fuzzification A6, FLRG G6, forecasting results 23.91 with Mape 1.11%. Results with the smallest mape with each travo travo 50 in each usage area 28.43, unbalanced 26%, fuzzification A5, FLRG G5, forecasting results 23.91 with Mape 0.28%. The results of this study can determine the location of the transformer along with unbalance, overload and the estimated amount of power consumption load for the use of transformer substations in an area, especially the ULP PT.PLN area for each region in PT.PLN (Persero) Krueng Geukuh. Then the results of this study can be used as a reference for monitoring population growth with excessive transformer power loads (overload) so that later you can install new transformer substations with a capacity according to the number of customers

Application of Artificial Intelligence to Predict CO2 Emissions: Critical Step towards Sustainable Environment

Prediction of carbon dioxide (CO2) emissions is a critical step towards a sustainable environment. In any country, increasing the amount of CO2 emissions is an indicator of the increase in environmental pollution. In this regard, the current study applied three powerful and effective artificial intelligence tools, namely, a feed-forward neural network (FFNN), an adaptive network-based fuzzy inference system (ANFIS) and long short-term memory (LSTM), to forecast the yearly amount of CO2 emissions in Saudi Arabia up to the year 2030. The data were collected from the “Our World in Data” website, which offers the measurements of the CO2 emissions from the years 1936 to 2020 for every country on the globe. However, this study is only concerned with the data related to Saudi Arabia. Due to some missing data, this study considered only the measurements in the years from 1954 to 2020. The 67 data samples were divided into 2 subsets for training and testing with the optimal ratio of 70:30, respectively. The effect of different input combinations on prediction accuracy was also studied. The inputs were combined to form six different groups to predict the next value of the CO2 emissions from the past values. The group of inputs that contained the past value in addition to the year as a temporal index was found to be the best one. For all the models, the performance accuracies were assessed using the root mean squared errors (RMSEs) and the coefficient of determination (R2). Every model was trained until the smallest RMSE of the testing data was reached throughout the entire training run. For the FFNN, ANFIS and LSTM, the averages of the RMSEs were 19.78, 20.89505 and 15.42295, respectively, while the averages of the R2 were found to be 0.990985, 0.98875 and 0.9945, respectively. Every model was applied individually to forecast the next value of the CO2 emission. To benefit from the powers of the three artificial intelligence (AI) tools, the final forecasted value was considered the average (ensemble) value of the three models’ outputs. To assess the forecasting accuracy, the ensemble was validated with a new measurement for the year 2021, and the calculated percentage error was found to be 6.8675% with an accuracy of 93.1325%, which implies that the model is highly accurate. Moreover, the resulting forecasting curve of the ensembled models showed that the rate of CO2 emissions in Saudi Arabia is expected to decrease from 9.4976 million tonnes per year based on the period 1954–2020 to 6.1707 million tonnes per year in the period 2020–2030. Therefore, the finding of this work could possibly help the policymakers in Saudi Arabia to take the correct and wise decisions regarding this issue not only for the near future but also for the far future.

Cloud height and thickness measurement based on a superconducting nanowire single-photon detector.

At present, the methods for measuring cloud height and thickness mainly include using micro-pulse lidar and microwave radiometer data. To further study cloud height and thickness, a superconducting nanowire single-photon detector (SNSPD) is applied to a lidar system for the first time, to the best of our knowledge, to analyze the cloud height and thickness. In the experiment, a 1.2-m-diameter horizon telescope is used for laser emitting and echo receiving, a 1064nm near-IR pulse laser with a single pulse energy of 4mJ is used as the system emission laser, and a 4-pixel SNSPD array detector is used as the end receiver to complete the echo photon reception. By analyzing the experimental data, the distributions of cloud height and cloud thickness can be obtained using the laser ranging system. The cloud cover condition on a certain day was measured, and the obtained cloud bottom height was about 1222m, cloud top height was about 1394m, and cloud cover thickness was about 172m. The difference between the cloud cover thickness and the forecast value was 28m. The cloud cover height and thickness measured by this method are true and credible.

Uncertain least squares estimation model based on relative error

Uncertain least squares estimation is one of the important methods to deal with imprecise data, which can fully consider the influence of given data on regression equation and minimize the absolute error. In fact, some scientific studies or observational data are often evaluated in terms of relative error, which to some extent allows the error of the forecasting value to vary with the size of the observed value. Based on the least squares estimation and the uncertainty theory, this paper proposed the uncertain relative error least squares estimation model of the linear regression. The uncertain relative error least squares estimation minimizes the relative error, which can not only solve the fitting regression equation of the imprecise observation data, but also fully consider the variation of the error with the given data, so the regression equation is more reasonable and reliable. Two numerical examples verified the feasibility of the uncertain relative error least squares estimation, and compared it with the existing method. The data analysis shows that the uncertain relative error least squares estimation has a good fitting effect.

PENERAPAN METODE FUZZY TIME SERIES MENGGUNAKAN PARTICLE SWARM OPTIMIZATION ALGORITHM UNTUK PERAMALAN INDEKS SAHAM LQ45

Stocks have a volatile nature and it is difficult to predict the ups and downs. Therefore, stock data forecasting is done by investors to get a picture of future results. Fuzzy Time Series is a time series method that is suitable for forecasting fluctuating stock data because it does not require the fulfillment of assumptions such as normality and stationarity, but the Fuzzy Time Series method has weaknesses in determining intervals. So that in this study, interval optimization will be carried out on Fuzzy Time Series with Particle Swarm Optimization algorithm to predict LQ45 stock index data, Particle Swarm Optimization algorithm is used because it produces more optimal interval values compared to other optimization methods such as Genetic Algorithm. The data to be used is the closing price of the LQ45 stock index on January 5, 2020 to December 26, 2021. Forecasting using the Fuzzy Time Series method produces a SMAPE value of 1.53%, then after optimization using the Particle Swarm Optimization algorithm, the SMAPE value decreases to 1, 27%. Therefore, it can be concluded that optimization using Particle Swarm Optimization on Fuzzy Time Series produces a more optimal forecasting value.

Post-Pandemic Steel Production Scenarios for Poland Based on Forecasts of Annual Steel Production Volume

Abstract The paper presents the results of forecasts made for the volume of steel production in Poland based on actual data for the period from 2006 to 2021 with forecasting until 2026. The actual data used for the forecasts included annual steel production volumes in Poland (crude steel) in millions of tons. Basic adaptive methods were used to forecast the volume of steel production for the next five years. When selecting the methods, the course of the trend of the studied phenomenon was taken into account. In order to estimate the level of admissibility of the adopted forecasting methods, as well as to select the best forecasts, the errors of apparent forecasts (ex post) were calculated. Errors were calculated in the work: RMSE Root Mean Square Error being the square root of the mean square error of the ex-post forecasts yt for the period 2006-2021; ? as the mean value of the relative error of expired forecasts y*t (2006-2021) – this error informs about the part of the absolute error per unit of the real value of the variable yt. Optimization of the forecast values was based on the search for the minimum value of one of the above-mentioned errors, treated as an optimization criterion. In addition, the value of the point forecast (for 2022) obtained on the basis of the models used was compared with the steel production volume obtained for 3 quarters of 2022 in Poland with the forecast for the last quarter. Forecasting results obtained on the basis of the forecasting methods used, taking into account the permissible forecast errors, were considered as the basis for determining steel production scenarios for Poland until 2026. To determine the scenarios, forecast aggregation was used, and so the central forecasts were determined separately for decreasing trends and for increasing trends, based on the average values of the forecasts obtained for the period 2022-2026. The central forecasts were considered the baseline scenarios for steel production in Poland in 2022-2026 and the projected production volumes above the baseline forecasts with upward trends were considered an optimistic scenario, while the forecasted production volumes below the central scenario for downward trends were considered a pessimistic scenario for the Polish steel industry.

Forecast Families: A New Method to Systematically Evaluate the Benefits of Improving the Skill of an Existing Forecast

A growing number of studies have investigated how forecast skill, i.e., predictive power, translates into forecast value, i.e., usefulness, for improving forecast-informed decisions. The relationship between skill and value is widely understood to be complex and case-specific, yet few methods enable its systematic exploration using realistic forecast errors. This paper addresses this gap by proposing a single-parameter linear scaling method to generate families of synthetic forecasts with the desired skill improvements on an existing hindcast (a retrospective forecast of already-observed events). The method is applicable to any quantity for which a deterministic or ensemble hindcast is available, and generates a set of forecasts with different skill but strictly proportional errors. This like-for-like comparison preserves the autocorrelation and cross-correlations of errors, and opens the door for thorough, yet easily interpretable, explorations of the relationship between skill and value of a realistic forecast. We apply this new method to seasonal precipitation hindcasts (produced by the fifth generation of the Seasonal forecasting System of the European Centre for Medium-range Weather Forecasts, ECMWF-SEAS5) in order to explore their value for improving the management of a water supply system in the UK. The application showed that although value generally increases with skill, the skill–value relationship is not necessarily linear, and it strongly depends on operational preferences and hydrological conditions (wet or dry years). It also suggests that the forecast families methodology can help water managers and forecast developers identify when a skill increase would be most valuable. This has the potential to foster productive two-way conversations between forecast producers and users.

Modeling Multi-horizon Electricity Demand Forecasts in Australia: A Term Structure Approach

The Australian Electricity Market Operator generates one-day ahead electricity demand forecasts for the National Electricity Market in Australia and updates these forecasts over time until the time of dispatch. Despite the fact that these forecasts play a crucial role in the decision-making process of market participants, little attention has been paid to their evaluation and interpretation. Using half-hourly data from 2011 to 2015 for New South Wales and Queensland, it is shown that the official half-hourly demand forecasts do not satisfy the econometric properties required of rational forecasts. Instead there is a relationship between forecasts and forecast horizon similar to a term structure model of interest rates. To study the term structure of demand forecasts, a factor analysis that uses a small set of latent factors to explain the common variation among multiple observables is implemented. A three-factor model is identified with the factors admitting interpretation as the level, slope and curvature of the term structure of forecasts. The validity of the model is reinforced by assessing the economic value of demand forecasts. It is demonstrated that simple adjustments to long-horizon electricity demand forecasts based on the three estimated factors can enhance the informational content of the official forecasts.

Optimization of investment strategies through machine learning

The main objective of this research is to develop a sustainable stock quantitative investing model based on Machine Learning and Economic Value-Added techniques for optimizing investment strategies. Quantitative stock selection and algorithmic trading are the two features of the model. Principal component analysis and economic value-added criteria are used in quantitative stock model for efficiently stocks selection, which may repeatedly select valuable stocks. Machine learning techniques such as Moving Average Convergence, Stochastic Indicators and Long-Short Term Memory are used in algorithmic trading. One of the first attempts, the Economic Value-Added indicators are used to appraise stocks in this study. Furthermore, the application of EVA in stock selection is exposed. Illustration of the proposed model has been done on United States stock market and finding shows that Long-Short Term Memory (LSTM) networks can more accurately forecast future stock values. The proposed strategy is feasible in all market situations, with a return that is significantly larger than the market return. As a result, the proposed approach can not only assist the market in returning to rational investing, but also assist investors in obtaining significant returns that are both realistic and valuable.

A bi-level framework for interactive competition and CPPs-based demand response

This paper proposes a multi-leader–follower framework for interactive competition among participants. To do so, a Stackelberg game model is formulated to take into account the price competition between leaders and captive power plants (CPPs). The retailer and the distribution company (DISCO) adopt a rival strategy to determine sale prices, aiming to maximize respective profit in a competitive market. DISCO pricing bound is set during the interaction process. The response at the lower level also affects hierarchical prices and CPP revenue. CPPs enact demand response viable through load shifting and peer-to-peer (P2P) energy trading. A quadratic penalty function is employed in the model to reduce the peak load demand and reshape the load profile, which brings the load consumption curve close to the forecast value. A general Nash bargaining game is utilized to incentivize P2P energy sharing with neighbors. To solve the multi-leader–follower model, a fixed-point iteration algorithm is proposed, which enables the model to reach convergence. Simulations are conducted to demonstrate the price–demand relationship and hierarchical interaction.

Solar Wind Data Assimilation in an Operational Context: Use of Near‐Real‐Time Data and the Forecast Value of an L5 Monitor

AbstractFor accurate and timely space weather forecasting, advanced knowledge of the ambient solar wind is required, both for its direct impact on the magnetosphere and for accurately forecasting the propagation of coronal mass ejections to Earth. Data assimilation (DA) combines model output and observations to form an optimum estimation of reality. Initial experiments with assimilation of in situ solar wind speed observations suggest the potential for significant improvement in the forecast skill of near‐Earth solar wind conditions. However, these experiments have assimilated science‐quality observations, rather than near‐real‐time (NRT) data that would be available to an operational forecast scheme. Here, we assimilate both NRT and science observations from the Solar Terrestrial Relations Observatory (STEREO) and near‐Earth observations from the Advanced Composition Explorer and Deep Space Climate Observatory spacecraft. We show that solar wind speed forecasts using NRT data are comparable to those based on science‐level data. This suggests that an operational solar wind DA scheme would provide significant forecast improvement, with reduction in the mean absolute error of solar wind speed around 46% over forecasts without DA. With a proposed space weather monitor planned for the L5 Lagrange point, we also quantify the solar wind forecast gain expected from L5 observations alongside existing observations from L1. This is achieved using configurations of the STEREO and L1 spacecraft. There is a 15% improvement for forecast lead times of less than 5 days when observations from L5 are assimilated alongside those from L1, compared to assimilation of L1 observations alone.

THEORETICAL AND ANALYTICAL SUBSTANTIATION OF THE FACTORS AFFECTING THE LEVEL OF SERVICE QUALITY MANAGEMENT OF RAILWAY TRANSPORT ENTERPRISES

The purpose of the study: theoretical and analytical substantiation of factors affecting the level of quality management of services of railway transport enterprises in Ukraine.The article analyzes the main scientific works of domestic and foreign scientists regarding the determination of the factors affecting the level of service quality management of enterprises, including railway transport enterprises. This is especially acute during the period of hostilities taking place on the territory of Ukraine. Thus, during the period of hostilities, the number of transportation services increased, especially due to the evacuation of the population and free travel. That is why the development of the potential of transport enterprises, including railway ones, is of crucial importance. The dynamics of changes in the transportation of passengers and cargo by modes of transport are presented in the paper with railway transport as a priority. The category of concepts " product quality" and "quality of services" has been analyzed.The internal (production, socio-psychological, human, organizational) and external (political, economic, social, technological, ecological, cultural, medical-biological) factors that affect the quality of services have been singled out, as well as the factor that affects the level of service quality management of railway transport enterprises, which, according to the authors, includes: reliability, safety, sensitivity, competence, accessibility, sociability, understanding, materiality, as physical parameters of the service, trust, courtesy. An integral indicator of the quality management level of railway transport enterprises is proposed. It has been found that in the future the construction of an integral indicator of the level of service quality management of railway transport enterprises and the determination of its forecast values may form the basis of the development of the state regional development strategy and separately be important for the development plans of railway transport enterprises.

2T-POT Hawkes model for left- and right-tail conditional quantile forecasts of financial log returns: Out-of-sample comparison of conditional EVT models

Conditional extreme value theory (EVT) methods promise enhanced forecasting of the extreme tail events that often dominate systemic risk. We present an improved two-tailed peaks-over-threshold (2T-POT) Hawkes model that is adapted for conditional quantile forecasting in both the left and right tails of a univariate time series. This is applied to the daily log returns of six large-cap indices. We also take the unique step of fitting the model at multiple exceedance thresholds (from the 1.25% to 25.00% mirrored quantiles). Quantitatively similar asymmetries in Hawkes parameters are found across all six indices, adding further empirical support to a temporal leverage effect in financial price time series in which the impact of losses is not only larger but also more immediate. Out-of-sample backtests find that our 2T-POT Hawkes model is more reliably accurate than the GARCH-EVT model when forecasting (mirrored) value at risk and expected shortfall at the 5% coverage level and below. This suggests that asymmetric Hawkes-type arrival dynamics are a better approximation of the true generating process for extreme daily log returns than GARCH-type conditional volatility. Our 2T-POT Hawkes model therefore presents a better-performing alternative for financial risk modelling.

ИҚТИСОДИЙ ЎСИШНИНГ АҲОЛИ ТУРМУШ ТАРЗИГА ТАЪСИРИ ВА УНИНГ ПРОГНОЗИ

This article describes the impact of economic growth on the lifestyle of the population. Economic growth and demographic changes in the regions of the Republic of Uzbekistan were studied and statistically analyzed. The state of the republic's regions was evaluated and divided into groups according to the compatibility of economic growth and demographic changes. On the basis of econometric models, mid-term forecast values for the main indicators representing the standard of living of the population have been developed. Scientifically based proposals have also been developed to ensure the stability of economic growth and improve the lifestyle of the population.

Analisis trend harga ayam broiler di masa pandemi covid-19 di Sulawesi Selatan

The Covid-19 pandemic has had an impact on all sectors, including the broiler farming sub-sector, both at the farmer level and at the marketer level. This study aims to determine trends in chicken prices and analyze the factors that influence chicken prices during the Covid-19 pandemic. This research was conducted April - May 2021 in South Sulawesi. The type of research used descriptive quantitative research. Data collection uses documentation method related chicken price data obtained from Indonesian People's Poultry Association (PINSAR) and direct interviews with PINSAR Chair of South Sulawesi. Data analysis used is descriptive analysis, qualitative analysis and time series forecasting methods, namely the moving average method and least square. The results showed that trend of chicken prices in 2020 fluctuated. Chicken prices in January-March 2020 fluctuated but were relatively controlled. The highest prices are in June until of December are very volatile. The factor that causes changes chicken prices the government's policy form of Large-Scale Social Restrictions so that many business sectors must be closed such as supply centers, restaurants, and others, causing difficulties in chicken distribution. The right forecasting method forecasting chicken prices moving average method because forecast value produced has relatively lower error rate than least square method.

A combined wind speed prediction model based on data processing, multi-objective optimization and machine learning

The ability to estimate wind speed accurately is crucial for optimizing the utilization of wind energy in power systems. The randomness of wind speed and the performance of prediction models are the two issues that have the greatest impact on wind speed prediction. This paper starts from the two aspects of digging wind speed characteristics and optimizing model performance. A new wind speed combined prediction model based on complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) and improved artificial bee colony algorithm (IABC) to optimize least squares support vector machine (LSSVM) performance. In order to reduce the randomness of the wind speed sequence and increase its predictability, CEEMDAN is first used to break down the wind speed sequence. Secondly, an LSSVM prediction model optimized by an improved artificial bee colony algorithm is established for each subsequence obtained by decomposition; finally, the wind speed forecast value is created by superimposing the results of each subsequence’s prediction. Case studies demonstrate that the combined prediction model put out in this study outperforms other models in terms of prediction performance.

Portfolio Construction Based on Combination of Individual Stocks and LSTM

With the development of the idea of portfolio optimization, it has become one of the important topics in the field of modern finance for achieving the balance between maximizing the return of assets and minimizing the risk. This study selected ten stocks from WIND and used LSTM Neural Network as the fundamental forecasting model. Based on the method of cyclic prediction, we predicted the asset’s return forecast value of the next day by rolling multi-dimensional historical features. Five stocks with the best outcomes were selected for optimization, using both the return component and the volatility, covariance matrix of the stocks’ returns as the covariance matrix to build the efficient frontier and to optimize the weighting. The Monte Carlo Simulation was used to build the maximum Sharpe ratio portfolio and minimum volatility portfolio. The maximum Sharpe ratio portfolio showed that the Midea and Mindray had the potential to profit dramatically at the risk of high volatility. However, relatively high volatility means the possibility of profiting is questionable, so a Minimum Volatility Portfolio was also conducted, which indicated conservative investors usually reduce the risk of their investment as much as possible. Whereas the max Sharpe ratio portfolio showing that risk-seeking investors are more willing to take risks if it can generate more profit. Overall, a hybrid intelligent algorithm based on cyclic prediction, Monte Carlo Simulation and artificial neural network was proposed, and the new applications of machine learning and mathematical methods in asset allocation were promoted.

A cognitive model for forecasting the stability of the economy under conditions of market uncertainty and risk

The article considers the theoretical foundations for predicting the stability of the Russian economy under conditions of market uncertainty and risk using a cognitive model. The relevance of the study lies in the fact that an acute problem in modern conditions is the question of the formation of methodological approaches for a balanced sustainable development of the economy and fi nance. The novelty lies in the fact that the study proposed an approach that involves the use of a cognitive model formed in the GraphViz environment using a semantic frame network in the form of graphs in the DOT programming language. An analysis of the dynamics of both macroeconomic indicators of the real sector of the economy and the parameters of the development of the fi nancial sector of the Russian Federation was carried out. Three perceptron AI models have been developed using the Deductor platform to predict the dynamics of the RF GDP. The criterion for the success of the predictive properties of AI models was the value of the average forecast error. The comparison was carried out every time, cycle by cycle, with the exclusion from the model of factors that have a weak relationship with the effective indicator — the forecast value of GDP and subsequent replacement with another one that has a higher value of the correlation coeffi cient. In addition, within the cycle, if necessary, the hyperparameters of the model can be changed: the number of hidden layers, the number of nodes on the input and hidden layers. In the proposed neural network, the architecture assume s, in addition to the input layer, the use of two hidden layers and an output layer with one parameter. However, in the experiment, the hyperparameters of the neural networks did not change. Neural networks showed high prediction accuracy.