Forecasting Process Research Articles

Examining Extreme Rainfall Forecast and Communication Processes in the South-Central United States

Abstract Extreme rainfall events are hazardous and costly. They have increased in parts of the United States, and climate models project that trend to continue. Effective communication of potential threats and impacts associated with extreme rainfall events is one of the foci of a weather forecaster’s job and aligns with the National Weather Service (NWS)’s mission to protect life and property. This research investigated how NWS forecasters processed and communicated information about extreme rainfall events that occurred in the south-central United States between 2015 and 2019. The study also explored forecasters’ perceptions of the relationship between the events and climate change and whether those perceptions impacted the forecasts, including how forecast information was communicated. Semistructured interviews were conducted with 21 NWS forecasters about how they internally processed and externally communicated model outliers and anomalous rainfall events. Thematic analysis of the interview data identified components of sensemaking and decision-making conceptual frameworks as well as principles of forecasting. These components were then combined to create an extreme event forecast communication process model to illustrate the findings. Although forecast and communication processes are complex and vary between offices and forecasters, the communication process model presents a high-level conceptualization of how forecasters translate highly technical and disparate material into usable information for their audiences within the context of rare meteorological events. Significance Statement This study presents an extreme event forecast communication process model that helps to explain how National Weather Service forecasters process and communicate extreme rainfall events. Forecasters were interviewed about their experience with extreme rainfall events. Effective communication of such events is important because they can lead to significant, and sometimes deadly, impacts. In the future, the extreme event forecast communication process model might provide a framework for best practices and be incorporated into forecaster training materials. Additional research is needed to determine whether the model applies to regions outside the south-central United States.

Prediction of Midwifery Services in Hospitals

Prediction is a forecasting process that will occur in the future with prior information, systematically in order to minimize errors. This study aims to determine the prediction of midwifery Indicators at Ir. Soekarno Sukoharjo in 2022-2024. This research is a descriptive study with a retrospective approach. The population of this study is the total number of deliveries in 2019-2021. The sample used is saturated sample. The results of this study obtained the value of the ratio of normal delivery, delivery with complications, cesarean section has increased in 2019-2021. The trend value of normal delivery has a tendency to increase by (0.007), the trend for delivery with complications has a tendency to increase by (0.020), trend of caesaria section has a tendency of increasing by (0.014), trend of abortion has a tendency of decreasing of (-0.03), trend of bleeding before delivery has a tendency of decreasing of (-0.001), trend of bleeding after delivery has a tendency of increasing of (0.001), trend of preeclampsia has a decreasing trend of (-0.011), the trend of eclampsia has a decreasing trend of (-0.001). The conclusion of this study is the prediction for 2022-2024 in normal delivery, delivery with complications, caesaria section, bleeding after delivery has increased every year. While abortion, bleeding before delivery, preeclampsia and eclampsia decreased.

Analisis Perencanaan dalam Kegiatan Ekstrakurikuler di Madrasah Aliyah Negeri Se-Kabupaten Tanah Datar

At the present time education is an aspect of life that has renewal to be discussed because it is a dimension that cannot be separated from the development of human activity as a social being with many reforms in the world of education the need for extracurricular activities to support student achievement which is useful in the future . The diversity of leadership, locations and extracurricular activities at Madrasah Aliyah Negeri throughout Tanah Datar district. This study aims to explain the process of the planning function in the management of extracurricular activities in MAN throughout Tanah Datar regency. This study used a qualitative approach which took place at MANs throughout Tanah Datar Regency. Informants from this study were Madrasah Principals, Deputy Madrasah Heads for Student Affairs and Superintendents of extracurricular activities except for MAN 1 Tanah Datar, only Deputy Head of Madrasahs for Student Affairs because the answers were concurrently Heads of Madrasahs and Extracurricular Advisors . Data collection is done by interview. The data obtained was analyzed with several stages of data reduction, data display and drawing conclusions. Researchers use triangulation of sources and use references in guaranteeing the validity of the data. The findings of the research results can be stated that the implementation of the planning function in the management of extracurricular activities in MAN throughout Tanah Datar Regency has been implemented well in general. However, in some planning processes have not gone well. As in the madrasa forecasting process, it only mentions the objectives of the extracurricular activities carried out, the program implementation strategy, the budget, and policy interpretation

Регресійні моделі спеціальної фізичної підготовленості тхеквондистів 12 14 років

Purpose: to develop regression models of special physical fitness of taekwondo players aged 12-14 years. Material and methods. The study was conducted at the public organization «Taekwondo Federation (WTF) of Ukraine». It was attended by 30 athletes specializing in taekwondo, aged 12-14 years, qualification 1-2 adult category. The following methods were used in the research: theoretical analysis and generalization of scientific and methodical literature and the Internet, pedagogical testing, methods of mathematical statistics. Results: it was established that indicators of special physical fitness depend on one, two, three and even four statistically significant independent variables (indicators of general physical fitness) within p<0,05-0,01. From regression models it is seen that the speed and power index, a swing of the left foot forward for 15 s and «Pistol» on the left foot for 30 s have statistically significant influence on the index of frequency of performance of lateral kicks in a trunk for 10 s alternately with both feet. It is established that the index of a side kick with a turn in opposite directions for 15 s in the upper level depends on a longitudinal twine on the left and right legs. A side kick with a 360° turn in 15 s with the left and right legs depends on a swing of the left leg forward in 15 s and the index of the right leg is also influenced by the speed and power index. The index of the reverse lateral kick for 15 s with the right foot statistically depends on the longitudinal twine on the left foot. The maximum number of strokes of nerio chagi alternately for 15 s depends on four indicators of special physical fitness: longitudinal twines on the right and left legs, a swing of the left leg for 15 s and a «pistol» on the right leg for 30 s. Conclusions. In modern conditions of training of sportsmen at the stages of long-term preparation for forecasting of success, experts in the field of physical culture and sport widely use the construction of regression models of preparedness. For the rapid construction of regression models of any order, it is necessary to use linear regression models with one independent variable. In order to detail the forecasting process, it is necessary to apply multiple analysis with a stepwise method that will allow to include in the regression equation the independent variables that have the highest coefficients of partial correlation with the dependent variable. The researches have established that in taekwondo fighters of 12-14 years old a statistically significant indicator of physical fitness which influences the manifestation of special is a longitudinal splits on the left and right legs, but the fascination with the development of flexibility of sportsmen can lead to the deterioration of results of speed and power orientation.

Predictability and forecast skill of solar irradiance over the contiguous United States

Current solar forecast verification processes place much attention on performance comparison of a group of competing methods. However, forecast verification ought to further answer how the best method within the group performs relative to the best-possible performance which one can attain under that forecasting situation, which makes the quantification of predictability and forecast skill immediately relevant. Unfortunately, the literature on the quantification of relative performance of solar irradiance has hitherto been lacking, and very few studies have focused on the spatial distributions of predictability and forecast skill of solar irradiance. The predictability and forecast skill of an atmospheric process depend on two concepts: (1) the growth of initial error in unresolved scale of motion, and (2) the forecast performance of the standard of reference. Based upon this formalism, predictability and forecast skill of solar irradiance in the United States are quantified and mapped. Through this study, a couple of common misconceptions in regard to irradiance predictability are refuted, and the original formulation of skill score revived.

Multivariate energy forecasting via metaheuristic tuned long-short term memory and gated recurrent unit neural networks

Energy forecasting plays an important role in effective power grid management. The widespread adoption of emerging technologies and the increased reliance on renewable sources of energy have created a need for a robust and accurate system for energy forecasting. This demand is becoming increasingly relevant due to the ongoing 2022 energy crisis. Modern power systems are very complex with many complicated correlations between various forecasting factors and parameters. Furthermore, renewable energy is often dependent on weather conditions, which complicates the process of forecasting. This work presents a novel artificial intelligence (AI) driven energy forecasting tuned deep learning framework. By formatting predictors as a time series, two variations of recurrent neural networks (RNN)s have been implemented: long-short-term memory (LSTM) and gated recurrent unit (GRU) neural networks. However, both approaches present several hyperparameters that require adequate tuning to attain desirable performance. Therefore, this work also proposes an improved version of a well know swarm intelligence algorithm, the sine cosine algorithm (SCA), tasked with tackling hyperparameter tuning for both approaches. To demonstrate the improvements made, three datasets have been constructed for evaluation from publicly available real-world data that contain relevant solar, wind, and power-grid load parameters alongside weather data. The proposed metaheuristic algorithm has been subjected to a comparative analysis with several contemporary metaheuristic algorithms to showcase the improvements made. The introduced metaheuristic demonstrated the best performance with a mean square error (MSE) rate for solar generation of only 0.0132 with LSTM methods and 0.0134 with GRU. Similar performance was observed for wind power generation forecasting with a MSE of 0.00292 with LSTM and 0.00287. When tackling power grid load forecasting a median MSE of 0.0162 was attained with LSTM and 0.01504 with GRU. Therefore there is great potential for tackling these tasks using the proposed approach. The best-performing models have been analyzed using SHapley Additive exPlanations (SHAP) to determine the factors that have the highest influence on energy generation and demand.

On the Lateral Entrainment Instability in the Inner Core Region of Tropical Cyclones

AbstractEntrainment of dry moat air with low equivalent potential temperature laterally into the eyewall and rainbands is a unique turbulent process in the inner‐core region of a tropical cyclone (TC). By analyzing in‐situ aircraft measurements collected by the reconnaissance flights that penetrated the eyewalls and rainbands of Hurricanes Rita (2005), Patricia (2015), Harvey (2017), and Michael (2018), as well as numerical simulations of Hurricanes Patricia (2015), and Michael (2018), we show that the moat air entrained into the eyewall and rainbands meets the instability criterion, and therefore, sinks unstably as a convective downdraft. The resultant positive buoyancy fluxes are an important source for the turbulent kinetic energy (TKE) in the eyewall and rainband clouds. This mechanism of TKE generation via lateral entrainment instability should be included in the TKE‐type turbulent mixing schemes for a better representation of turbulent transport processes in numerical forecasts of TCs.

A Novel Mathematical Study on the Predictions of Volatile Price of Gold Using Grey Models

In the history of the gold market, contemporary gold prices are higher than the previous values, and the current gold market is highly non-linear and unpredictable. Gold is the most popular precious metal for investment out of all the precious metals. The gold market, like other markets, is vulnerable to speculation and volatility. Gold has served as a secure base in several countries when compared to other precious metals used for investment. In this study, we suggest a time series model for predicting daily variations in the amount of gold per gram in Indian rupees. To increase the forecasting accuracy, we use a hybrid prediction method known as the Grey-Fourier Markov model which includes Grey models (GM), Fourier series, and Markov state transition. Here, we divide the forecasting process into three steps. The first step is to simulate the data of daily volatile price of gold using GM (1, 1), GM (2, 1), and Grey Verhulst models and also to calculate corresponding residual errors. In the second step, we utilize the residual error produced by the above grey models to predict the trend of the gold price with the help of the Fourier series and Markov Model. In the third step, we use hybrid grey models to improve the precision. Finally, we conclude that the proposed methodology outperforms the aforementioned strategies in terms of results.

Learning to Forecast: The Probabilistic Time Series Forecasting Challenge

We report on a course project in which students submit weekly probabilistic forecasts of two weather variables and one financial variable. This real-time format allows students to engage in practical forecasting, which requires a diverse set of skills in data science and applied statistics. We describe the context and aims of the course, and discuss design parameters like the selection of target variables, the forecast submission process, the evaluation of forecast performance, and the feedback provided to students. Furthermore, we describe empirical properties of students’ probabilistic forecasts, as well as some lessons learned on our part.

TransFNN: A Novel Overtemperature Prediction Method for HVDC Converter Valves Based on an Improved Transformer and the F-NN Algorithm.

Appropriate cooling of the converter valve in a high-voltage direct current (HVDC) transmission system is highly significant for the safety, stability, and economical operation of a power grid. The proper adjustment of cooling measures is based on the accurate perception of the valve's future overtemperature state, which is characterized by the valve's cooling water temperature. However, very few previous studies have focused on this need, and the existing Transformer model, which excels in time-series predictions, cannot be directly applied to forecast the valve overtemperature state. In this study, we modified the Transformer and present a hybrid Transformer-FCM-NN (TransFNN) model to predict the future overtemperature state of the converter valve. The TransFNN model decouples the forecast process into two stages: (i) The modified Transformer is used to obtain the future values of the independent parameters; (ii) the relation between the valve cooling water temperature and the six independent operating parameters is fit, and the output of the Transformer is used to calculate the future values of the cooling water temperature. The results of the quantitative experiments showed that the proposed TransFNN model outperformed other models with which it was compared; with TransFNN being applied to predict the overtemperature state of the converter valves, the forecast accuracy was 91.81%, which was improved by 6.85% compared with that of the original Transformer model. Our work provides a novel approach to predicting the valve overtemperature state and acts as a data-driven tool for operation and maintenance personnel to use to adjust valve cooling measures punctually, effectively, and economically.

Short-Term Probabilistic Forecasting Method for Wind Speed Combining Long Short-Term Memory and Gaussian Mixture Model

Wind speed forecasting is advantageous in reducing wind-induced accidents or disasters and increasing the capture of wind power. Accordingly, this forecasting process has been a focus of research in the field of engineering. However, because wind speed is chaotic and random in nature, its forecasting inevitably includes errors. Consequently, specifying the appropriate method to obtain accurate forecasting results is difficult. The probabilistic forecasting method has considerable relevance to short-term wind speed forecasting because it provides both the predicted value and the error distribution. This study proposes a probabilistic forecasting method for short-term wind speeds based on the Gaussian mixture model and long short-term memory. The precision of the proposed method is evaluated by prediction intervals (i.e., prediction interval coverage probability, prediction interval normalized average width, and coverage width-based criterion) using 29 monitored wind speed datasets. The effects of wind speed characteristics on the forecasting precision of the proposed method were further studied. Results show that the proposed method is effective in obtaining the probability distribution of predicted wind speeds, and the forecast results are highly accurate. The forecasting precision of the proposed method is mainly influenced by the wind speed difference and standard deviation.

SHM-informed life-cycle intelligent maintenance of fatigue-sensitive detail using Bayesian forecasting and Markov decision process

Civil and maritime engineering systems must be efficiently managed to control the failure risk at an acceptable level as their performance is gradually degraded throughout the operational life, caused by fatigue and corrosion. Structural health monitoring develops a timely capability to assess the structural condition and performance metrics. However, using actual long-term monitoring data to guide the life-cycle management under stochastic environments has not been sufficiently studied. To realize an optimal maintenance strategy within the service life, an integrated monitoring-based optimal management framework is developed on the basis of the partially observable Markov decision processes (POMDPs) and Bayesian forecasting. In the proposed framework, the stochastic fatigue processes are quantified by the state transition matrix. The Bayesian dynamic linear model is embedded in POMDPs as a continuous observation part to forecast the cycling impacts and estimate the deterioration rate using long-term dynamic strain responses. In addition, making use of the special features of the problem considered in this paper, an adaptive discretization strategy is proposed to alleviate the complexity of large discrete observed spaces in the POMDP. The applicability and feasibility of the framework are evaluated by intelligent maintenance of fatigue-sensitive components with real-world monitoring data. After solving the POMDP by an efficient offline solver, the results obtained in this paper demonstrate that structural interventions are uneconomical to extend the life when a welded detail is approaching its end of life due to the normal service. Furthermore, if multiple interventions are available, the framework can find optimal maintenance actions based on the trade-off between long-term utility and the corresponding cost. This framework as the prototype could also be adjusted to aid life-cycle intelligent maintenance of other types of components under different deterioration scenarios.

DyFraNet: Forecasting and backcasting dynamic fracture mechanics in space and time using a 2D-to-3D deep neural network

The dynamics of material failure is a critical phenomenon relevant to a range of scientific and engineering fields, from healthcare to structural materials. We propose a specially designed deep neural network, DyFraNet, which can predict dynamic fracture behaviors by identifying a complete history of fracture propagation—from the onset of cracking, as a crack grows through the material, modeled as a series of frames evolving over time and dependent on each other. Furthermore, the model can not only forecast future fracture processes but also backcast to elucidate past fracture histories. In this scenario, once provided with the outcome of a fracture event, the model will reveal past events that led to this state and can also predict future evolutions of the failure process. By comparing the predicted results with atomistic-level simulations and theory, we show that DyFraNet can capture dynamic fracture mechanics by accurately predicting how cracks develop over time, including measures such as the crack speed, as well as when cracks become unstable. We use Gradient-weighted Class Activation Mapping, Grad-CAM, to interpret how DyFraNet perceives the relationship between geometric conditions and fracture dynamics, and we find that DyFraNet pays special attention to the areas around crack tips that have a critical influence in the early stage of fracture propagation. In later stages, the model pays increased attention to the existing or newly formed damaged regions in the material. The proposed approach offers the potential to accelerate the exploration of dynamical processes in material design against failure and can be adapted for all kinds of dynamical problems.

Estimation of properties of ultra great workability concrete by optimized ANFIS models

The mechanical properties of the ultra-great workability concrete (UGWC) are deeply related to the weights of components, curing period and condition, and occasionally property of admixtures. This study aimed to appraise the usefulness of the adaptive neuro-fuzzy inference system (ANFIS) technique for forecasting the compressive strength of UGWC and enhancing the accuracy of the literature. To outline the forecasting process, two improved ANFIS were suggested, in which determinative variables of them were determined by metaheuristic algorithms named imperialist competitive algorithm (ICA) and multi-verse optimizer (MVO) algorithms. For this purpose, 170 data samples were collected from published literature separated accidentally for the train and test phase. The calculated performance criteria for proposed ANFIS models demonstrate that both ICA-ANFIS and MVO-ANFIS models can result in justifiable workability for fc of the UGWC prediction procedure. The MVO-ANFIS model could outperform ICA-ANFIS regarding all criteria. For instance, the value of R2 and VAF for the ICA-ANFIS model are roughly smaller than the MVO-ANFIS model, at 0.9012 and 90% in the training dataset and 0.8973 and 89% in the testing stage, respectively. While the best values of criteria have belonged to the MVO-ANFIS model, with R2 at 0.937 and 0.944 for the train and test phases, respectively. Overall, the hybrid MVO-ANFIS model can obtain higher workability than ICA-ANFIS and literature (R2 at 0.801), where causes are recognized as the proposed model.

The Use of Ensemble Clustering on a Multimodel Ensemble for Medium-Range Forecasting at the Weather Prediction Center

Abstract This article introduces an ensemble clustering tool developed at the Weather Prediction Center (WPC) to assist forecasters in the preparation of medium-range (3–7 day) forecasts. Effectively incorporating ensemble data into an operational forecasting process, like that used at WPC, can be challenging given time constraints and data infrastructure limitations. Often forecasters do not have time to view the large number of constituent members of an ensemble forecast, so they settle for viewing the ensemble’s mean and spread. This ignores the useful information about forecast uncertainty and the range of possible forecast outcomes that an ensemble forecast can provide. Ensemble clustering could be a solution to this problem as it can reduce a large ensemble forecast down to the most prevalent forecast scenarios. Forecasters can then quickly view these ensemble clusters to better understand and communicate forecast uncertainty and the range of possible forecast outcomes. The ensemble clustering tool developed at WPC is a variation of fuzzy clustering where operationally available ensemble members with similar 500-hPa geopotential height forecasts are grouped into four clusters. A representative case from 15 February 2021 is presented to demonstrate the clustering methodology and the overall utility of this new ensemble clustering tool. Cumulative verification statistics show that one of the four forecast scenarios identified by this ensemble clustering tool routinely outperforms all the available ensemble mean and deterministic forecasts. Significance Statement Ensemble forecasts could be used more effectively in medium-range (3–7 day) forecasting. Currently, the onus is put on forecasters to view and synthesize all of the data contained in an ensemble forecast. This is a task they often do not have time to adequately execute. This work proposes a solution to this problem. An automated tool was developed that would split the available ensemble members into four groups of broadly similar members. These groups were presented to forecasters as four potential forecast outcomes. Forecasters felt this tool helped them to better incorporate ensemble forecasts into their forecast process. Verification shows that presenting ensemble forecasts in this manner is an improvement on currently used ensemble forecast visualization techniques.

Forecasting of University Students' Performance Using A Hybrid Model of Neural Networks and Fuzzy Logic

Abstract: Artificial intelligence techniques can be applied in forecasting the academic performance of university students, with aim of detecting the factors that influence their learning process which allows instructors and university administration to take more effective actions to increase the university student's performance. Identifying the students' performance will improve the quality of education which will be through analyzing and forecasting the students' performance at the course level and degree level. This research focuses on first-year students' performance in two university-requirement courses, depending on features such as attendance, assessment marks, exams, assignments, and projects. Forecasting the students' performance in the whole degree will depend on these features; high school average, Grade Point Average (GPA) for each semester, drop courses, selected core courses in the degree, period of study, and final GPA. A hybrid Adaptive Neuro-Fuzzy Inference System (ANFIS) model was used toperform the forecasting process. In this way, based on the datasets collected from the selected courses, or the whole degree, the future results can be forecasted and suggestions can be made to carry out corrective steps to improve the final results. The experiments result of the applied models performed that ANFIS-Grid outperforms the ANFIS-Cluster, wherein each model produces the lowest error of 0.7%, where it just fails in one sample from thirteen samples, while the ANFISCluster after modification produces an error equal to 0.15%. Keywords:University Student Performance, Forecasting, Fuzzy logic, Neural Network, Adaptive Neuro-Fuzzy Inference System.

Line Balancing Based on Error Rate Estimation with Artificial Neural Networks in Assembly Line Operations

In this study, in the assembly line systems consisting of the operations in interaction with each other; To reduce the number of faulty products, to prevent poor quality and to reduce the production time, Error Ratio Estimation with Artificial Neural Networks and probabilistic Line Balancing method have been performed. The error rate estimation provides information on which jeans models should be applied in the improvement work to eliminate existing errors in place. In the study, using the Levenberg - Marquardt Learning Algorithm, machine learning was determined by the experimental design method. At the same time, it has been used as an artificial intelligence algorithm in the multi-directional decision making stages, estimation and line balancing parts. In Assembly Line Equilibration, it has been aimed to re-stabilize the unbalanced line with the influence of post-forecasting process recovery. The Probabilistic Line Balancing method has been used because the processing times are stochastic (variable) and statistical data and mathematical algorithms (digital algorithms can be created). When the results are examined, a successful forecasting process has been carried out for two different five-pocket jeans models which has been selected and it has been seen that the work components of the probabilistic line balancing method enable it to be precisely assigned to work stations. And it has given reliable results.

Application of machine learning to cluster hotel booking curves for hotel demand forecasting

Accurate demand forecasting is integral for data-driven revenue management decisions of hotels, but an unprecedented demand environment caused by COVID-19 pandemic has made the forecasting process more difficult. This study aims to propose a new approach for daily hotel demand forecasting by using clusters of stay dates generated from historical booking data. This new approach is fundamentally different from traditional forecasting approaches for hotels that assume the booking curves and patterns tend to be similar during the trailing period approach. In this study, historical booking curves are clustered by a machine learning algorithm using an auto-regressive manner and the additive pickup model is used to forecast daily occupancy up to 8 weeks. The efficacy of a new forecasting approach is tested using real hotel booking data of three hotels and results show that forecasts of hotel demand are more accurate when they are generated at cluster-level for all forecasting horizons.

Financing Biofuel Through Green Sukuk Corporate: Stage, Potential, and Maturity

Climate mitigation and adaptation policy financing have emerged as a critical topics in climate discussions. Effective financing schemes are often debated as potential mitigation measures, with the proceeds going toward adaptation activities. This research aims to investigate the viability of green sukuk corporate as a source of financing for biofuel development initiatives in Indonesia. A forecasting process, indexation, and early warning system (EWS) method are used to test the model to assess possible risks at a specific maturity level. In this study, factor variables include GDP, Inflation, the Jakarta Islamic Index (JII), sukuk corporate outstanding, and accumulated sukuk corporate issued. The main findings of this study suggest that to generate sustainable biofuel finance, three-stage models/concepts must be built; the commitment to business as usual, the greenhouse gas mitigation stage, and the debt repayment stage. In terms of potential, the trend of green corporate sukuk is toward greater participation by sovereigns and non financial corporations. In terms of maturity, corporate green sukuk requires a longer repayment period than conventional bonds, with a time tenor of 3–5 years being suitable. Finally, we show that the issuance of green corporate sukuk is supported by macroeconomic stability. The bond scheme can be repaid and carried out to provide sustainable benefits for renewable energy.

A Heuristic Approach to Forecasting and Selection of a Portfolio with Extra High Dimensions

The performance of a financial portfolio depends on the output of two tasks: first, a forecasting process, where quantities of interest for the investors, such as the rate of return and risk for each stock, are predicted into the future, and second, an optimization process, where those individual stocks are formed into the portfolio optimizing the combined risk and reward features. However, in very large dimensions, when the number of stocks is high, those two quantitative problems often become intractable because of a loss in precision. This paper introduces a forecasting and portfolio formation strategy in multiple periods based on the splitting of the multivariate forecasting model into multiple bivariate forecasting models and updating investment weights at each period based on the predicted target quantities for the returns and the covariances. The methodology proposed is suitable for a very large portfolio of assets. The experimental results are based on a sample of one thousand stocks from the Chinese stock market. For such a large sample, the forecast and optimization process is executed speedily. The investment strategies are benchmarked with the equally weighted portfolio. In the long run, they offer a better investment performance in terms of a higher rate of return or lower risk, compared with this portfolio, demonstrating the applicability and economic value of the proposed methodology in practice.