Raw Stock Research Articles

Research on stock prediction based on CED-PSO-StockNet time series model

To tackle the challenge of low accuracy in stock prediction within high-noise environments, this paper innovatively introduces the CED-PSO-StockNet time series model. Initially, the model decomposes raw stock data using the Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) technique and reconstructs the components by estimating their frequencies via the extreme point method. This process enhances component stability and mitigates noise interference. Subsequently, an Encoder-Decoder framework equipped with an attention mechanism is employed for precise prediction of the reconstructed components, facilitating more effective extraction and utilization of data features. Furthermore, this paper utilizes an Improved Particle Swarm Optimization (IPSO) algorithm to optimize the model parameters. On the Pudong Bank dataset, through ablation experiments and comparisons with baseline models, various optimization strategies incorporated into the proposed CED-PSO-StockNet model were effectively validated. Compared to the standalone LSTM model, CED-PSO-StockNet achieved a remarkable 45.59% improvement in the R2 metric. To further assess the model’s generalization capability, this paper also conducted comparative experiments on the Ping An Bank dataset, and the results underscored the significant advantages of CED-PSO-StockNet in the domain of stock prediction.

Reinforcement Learning-Based Multimodal Model for the Stock Investment Portfolio Management Task

Machine learning has been applied by more and more scholars in the field of quantitative investment, but traditional machine learning methods cannot provide high returns and strong stability at the same time. In this paper, a multimodal model based on reinforcement learning (RL) is constructed for the stock investment portfolio management task. Most of the previous methods based on RL have chosen the value-based RL methods. Policy gradient-based RL methods have been proven to be superior to value-based RL methods by a growing number of research. Commonly used policy gradient-based reinforcement learning methods are DDPG, TD3, SAC, and PPO. We conducted comparative experiments to select the most suitable method for the dataset in this paper. The final choice was DDPG. Furthermore, there will rarely be a way to refine the raw data before training the agent. The stock market has a large amount of data, and the data are complex. If the raw stock market data are fed directly to the agent, the agent cannot learn the information in the data efficiently and quickly. We use state representation learning (SRL) to process the raw stock data and then feed the processed data to the agent. It is not enough to train the agent using only stock data; we also added comment text data and image data. The comment text data comes from investors’ comments on stock bars. Image data are derived from pictures that can represent the overall direction of the market. We conducted experiments on three datasets and compared our proposed model with 11 other methods. We set up three evaluation indicators in the paper. Taken together, our proposed model works best.

Economic Echoes of Conflict: Evaluating the Palestine-Israel War’s Influence on Middle Eastern Markets

ABSTRACT This study examines the Palestine-Israel conflict’s effects on Middle Eastern financial markets, including conventional and Islamic indices. Employing wavelet cross-correlation, global VAR (GVAR), and Granger causality analyses, we identify complex patterns in pre-conflict geopolitical risk (GPR) and stock returns, including diverse lead/lag behaviors and amplitude fluctuations. Post-conflict, these dynamics show smoother adjustments and stronger cross-correlations. The pre-conflict wavelet GVAR analysis reveals country-specific reactions to anticipated GPR shocks, marked by asymmetric responses starting around 20 days post-shock and varying across nations. This period also features significant shock spillovers in stock returns, both positive and negative. During the conflict, initial reactions include substantial spikes in raw stock returns, suggesting possible co-crash scenarios. These evolve into predominantly positive short-term shock spillovers, with medium and long-term responses suggesting stock markets as potential safe havens. Lastly, wavelet Granger causality analysis reveals bidirectional causality between GPR and stock returns over the long term, with specific countries showing varied causality patterns during the conflict. The inclusion of Islamic indices demonstrates homogeneous responses to GPR shocks, similar to conventional markets, highlighting the integrated nature of these markets. This study underscores the complex temporal dynamics of market responses to geopolitical shocks and provides insights for policymakers and investors.

Effect of TiO2 content on the thermal control properties of Al2O3-xTiO2 composite coatings prepared by supersonic plasma spraying technology

The main challenge faced by spacecraft is the large temperature difference in its operating environment. Thermal control coatings prepared on spacecraft and instrument surfaces are currently the most efficient ways for heat dissipation and control. In this work, Al2O3-xTiO2 composite coatings with different TiO2 contents were prepared on 7075-Al alloy substrate by supersonic plasma spraying technology. The microstructure, phase composition, mechanical properties, thermal control properties, and corrosion resistances of the coatings were investigated. The raw stock feeds were mainly composed of α-Al2O3 and anatase TiO2, but the coatings were mainly γ-Al2O3 and rutile TiO2. The average Vickers microhardness of the coatings decreased from 1198.9 to 810.4 HV0.2 with the increase of TiO2 contents, but the elastic modulus increased from 158.5 to 244.3 GPa. The thermal control properties of the coatings were promoted with the growth of TiO2 contents, and the absorptance increased from 27.1 to 89.2% with the emittance from 83.7 to 86.5%. The corrosion potential and corrosion resistance of the coating gradually increased with TiO2 content due to its gradually improved hydrophobicity. This work broadens the application boundary of Al2O3-xTiO2 composite coating and provides an innovative idea for material selection of thermal control coatings.

Substantiating the reliability conditions for the production process at metallurgical enterprises through the fault-tolerant functioning of the system «extraction of raw materials – technological railroad routes – metallurgical production»

The object of this study is the process of formation of insurance reserves at enterprises in the metallurgical industry. Under conditions of uneven supply of raw materials to metallurgical enterprises due to disruption of the transportation process or other reasons, there is a need to create insurance stocks in order to ensure the continuity of production. At the same time, it is necessary to take into account existing restrictions, such as the limited capacity of railroad sections and the impossibility of organizing parallel movement of trains, etc. The presence of these limitations makes it impossible to use classical methods for solving similar problems, such as linear programming. Therefore, to resolve the task, a simulation model was built, based on the discrete-event principle in the AnyLogic University Researcher environment using Oracle libraries and the Java SE compiler. With the help of the model, the process of rotation of dispatch routes at the railroad yard with multiple suppliers and one consignee was formalized. The optimization criterion was chosen to be the minimum deviations of fluctuations in reserves of iron ore concentrate and coke. Analysis of the simulation results revealed that the optimal size of the fleet of railroad routes on the selected rotation polygon is 30 units; at the same time, their utilization rate will be 65 %. It was also established that fluctuations in raw material stocks have a «natural character», which is confirmed by the normal distribution of the density of stock volumes. Under these conditions, the value of fluctuations in the volumes of the main raw materials will be ±13115 t/day for iron ore concentrate, and ±5298 t/day for coke. Reducing the range of fluctuation of raw materials volumes could make it possible to optimize the costs of creating stocks and streamline the transport work of the enterprise for providing raw materials

Pemodelan Komponen Sistem Enterprise Resource Planning pada Industri Produksi Minyak

The digitalization of technology in the current era of globalization has brought many changes to the industry. The emergence of Enterprise Resource Planning (ERP) functions to integrate all departments and industrial business functions, especially in the oil production sector. ERP systems simplify business processes by integrating key functions from various departments. The business processes in the oil production industry are currently not yet running, which has given rise to problems with errors in purchasing goods from suppliers, inaccurate calculations of raw material usage, raw material stocks not being updated quickly, and purchasing reports not being generated automatically. Based on the background of these problems, the industry requires a component modeling that helps the ERP implementation process. Component modeling allows users in industry to understand ERP systems better without being overwhelmed by product or technical details. This research aims to define the ERP system components that are taken into consideration in its implementation. The research stages are divided into five, namely pre-implementation, analysis, design, construction and implementation. The results of the research are component model designs in terms of software, process flow, user mindset, and change management that will be used in implementing the ERP system

SISTEM INFORMASI PENGELOLAAN PRODUKSI KAIN TENUN DI BUTIK TENUN JEPARA

This research aims to develop an information system for managing the production of woven fabrics at Butik Tenun Jepara. This system is designed to enhance operational efficiency and facilitate data storage by transitioning from manual to digital record-keeping. The system was developed using the waterfall method, starting from requirements analysis, design, implementation, and testing. The implementation results show that this information system successfully improves the efficiency of production data and raw material stock management, minimizes recording errors, and accelerates the production process. The system also features basic authentication to differentiate between admin and employee access, ensuring data security and privacy.

Optimization of Raw Material Inventory using Always Better Control (ABC) Analysis and Economic Order Quantity (EOQ) Method Approach in the Warehouse of a Bolt Manufacturing Factory in Indonesia

There is a problem in the raw material procurement process at the Contractor Company, such as running out and excess stock of raw materials, as well as difficulties in determining how many raw materials to order that meet the company's economic value. Running out of raw material stock results in delays in production activities, while excess raw material stock can fill warehouse capacity, thereby increasing storage costs. To overcome this problem, research was carried out using a quantitative descriptive method to determine the level of production cost efficiency and production effectiveness level in order to achieve optimization of raw material supplies using Always Better Control (ABC) Analysis and the Economic Order Quantity (EOQ) Method at Bolt Companies. ABC analysis plays a role in determining which raw materials have the highest level of demand and the EOQ method plays a role in determining the amount of raw materials to be ordered in order to meet the company's economic value. The research results show that the combination of ABC Analysis and EOQ Method can reduce ordering costs and raw material inventory. There are 4 items out of 10 raw material items that are included in Category A or the most prioritized category. From the results of calculations using the EOQ method, the Bolt Company can save total orders and raw material inventory (TIC) in the period January to December 2023 amounting to IDR 2,147,403,-.

Food Safety Risk Analysis of Songkem Duck Using Failure Mode and Effect Analysis (FMEA) Method

Food safety is an essential aspect of human health. Food processed without paying attention to food safety regulations can harm consumer health. This research aims to 1) identify activities with food safety risks, 2) determine the sequence of food safety risks that will be followed up, and 3) determine appropriate food safety risk mitigation. This research uses the Failure Mode and Effect Analysis (FMEA) method and fishbone diagrams. A case study was conducted on the Songkem pak Soleh Bangkalan duck supply chain. The research results show that activities that pose a food safety risk include receiving raw materials, storing raw material stocks, using raw materials and BTP, sanitizing production facilities, and storing finished products. The priority order of food safety risks in the Songkem duck supply chain is based on the FMEA method: storage of finished products, sanitation of production facilities, and storage of raw material stocks. Risk mitigation can be done to prevent food safety risks in storing raw material stocks and storing finished products, namely by controlling water activity (aw) and acidity factor (pH); and controlling the room's atmosphere. Meanwhile, to prevent risks due to sanitation hygiene, namely holding training to increase awareness of the importance of sanitation hygiene for restaurant employees monitoring and maintaining sanitation hygiene in the production environment.

Implementing the Variance-Covariance Method for Assessing Market Transaction Risks in Raw Material Sector Stocks

The capital market plays a crucial role in supporting a country's economic growth. Besides being a funding source, the capital market also serves as an investment avenue for investors, particularly through stocks. Every investor must be willing to bear risks in line with their targeted returns. Risk is defined as the uncertainty of future outcomes due to market condition changes, and VaR (Value at Risk) is used to determine the tolerated loss at a certain confidence level. This study discusses the application of the Value at Risk (VaR) method using the Variance-Covariance approach to mitigate market risks in the portfolio of raw material sector stocks. The study focuses on two raw material sector stocks in Indonesia, assuming a normal distribution of asset price changes. The measurement results indicate that with an investment of Rp. 100,000,000.00, a 95% confidence level, and a 1-day period, the VaR of the portfolio of these five stocks is Rp. 2,769,750.00. This research provides critical insights to assist investors in understanding and managing portfolio risks, making VaR a key indicator to measure potential future risks and laying the foundation for decision-making in risk management.

Research on stock trend prediction based on grey wolf optimized RF and SVM models

The volatility of the stock market has a profound impact on the stability of the financial market, and then has a significant effect on the overall economic situation, so the accurate prediction of stock trend has always been the focus of research in the financial field. In this paper, the raw minute-level stock data of SSE 50 and CSI 300 in 2021 are normalized, and the historical training and test sets of daily stocks for model training and testing are established based on the datasets. The RF-SVM model based on the gray wolf optimization algorithm is constructed to compare the traditional support vector machine and random forest model, and the relevant performance indexes are calculated. In this study, the RF-SVM model based on gray wolf optimization is highly correlated with the characteristics of stock data, and the prediction accuracy of stock index data is more than 85%. The cross-validation score is over 0.77 and the overall weighted score is as high as 0.98. Compared with the SVM and random forest models under the default parameters, the RF-SVM model based on gray wolf optimization has an average advantage of 25% in performance indicators. The generalization ability is increased by about 26%; The fitting error was reduced by about 51.15%; The overall average score advantage is about 34%. These results prove that the RF-SVM model of gray wolf optimization has superior performance and significant optimization effect in stock prediction, and compared with the traditional grid search optimization algorithm, gray wolf optimization has excellent adaptability and can gradually obtain the global optimal parameter configuration.

Models for optimising the volume of material flows in the technological chain of corporate vertically integrated structures of the agricultural sector

The relevance of this study lies in the need to optimise supply cycles and volumes in value chains, which helps to reduce costs and increase the profitability of agricultural enterprises. The purpose of this study was to investigate and optimise the costs of initial material flows in the production subsystems of corporate vertically integrated structures of the agricultural complex under conditions of non-stationary demand. To fulfil this purpose, the study investigated the relationship between the amount of raw material stock stored in the production subsystem and the time of its consumption, based on which an extended model of the economic order quantity (EOQ) was considered, which, apart from the defined costs, also considers the costs of raw material shortages associated with the inability to fulfil deliveries and losses associated with supply failures caused by the unpredictability (stochasticity) of the order flow itself. It was found that in continuous production systems there is an opportunity to reduce the costs associated with failures by using an additional regular supply batch. For this, the mathematical “point-of-order” model was built based on the theory of mass service, which allows determining not only the best point to order, but also the optimal amount of the safety stock. A model for optimising the volume of material flows was proposed, which combines the model of the economic order quantity order adapted for use in product subsystems of corporate integrated structures of the agricultural complex and the “point-of-order” model, which allows calculating the minimum size of the insurance stock of raw materials using the tools of operations research. As an example, the material flow was optimised for Kivshovata Agro LLC. The findings of the study, such as the use of analytical tools and models for determining the economic order quantity and safety stock, can be used by the management of agricultural enterprises to improve the efficiency of material flow management

Analisis Manajemen Persediaan Bahan Baku Pada Pabrik Tahu Ditinjau Dari Perspektif Bisnis Islam

Production problems are a very important problem for business actors because they can affect the profits they earn. The smoothness of production itself is influenced by whether or not the raw materials will be used. In this case, raw material inventory management can help reduce possible risks. Raw material inventory management is the most active element in company operations which is continuously obtained. In this case, researchers use the Safety Stock, Economiq Order Quantity (EOQ) and Reorder point inventory management methods to optimize the purchase of raw material inventory so that it becomes optimal and efficient. In this research, problems were found at the Tofu Factory regarding raw material supplies. In this case, the Tofu Factory always experiences a shortage of raw material stock and experiences waste in the costs incurred. This resulted in the Tofu Factory experiencing delays in deliveries to consumers. The results of the analysis show the use of raw material inventory management methods applied at the Jagabaya tofu factory, namely SafetyStock, Economic Order Quantity (EOQ) and Reorder Point. The implementation of this method is not optimal so this method does not work as it should because of several inhibiting factors. The management of raw material supplies at the Jagabaya tofu factory still does not use a structured method, so that in the production process stock runs out often occur. Therefore, raw material inventory management at tofu factories is only based on estimated sales numbers without clear calculations.

Pengendalian Persediaan Bahan Baku Petis Udang dengan Menggunakan Metode Economic Order Quantity (Eoq) di Ud. Agung Jaya

Raw material inventory is very important for companies. UD. Agung Jaya is a company that operates in the food sector, namely Petis Udang. Problems at UD. Agung Jaya has raw material stock problems, namely a shortage or excess of raw materials. The aim of this research is to help optimize UD costs of UD. Agung Jaya. This research uses raw material purchase data for shrimp heads, sugar, and flour which is processed by forecasting calculations for 12 periods or 1 year into the future using the single exponential smoothing (SES) time series forecasting method. The aim is to determine the need for raw materials so that there are no shortages or excesses of raw materials during the ongoing production process, and the efficiency of raw material needs in this research. The results of the research show that the raw material for shrimp heads has a mape error value of 24, sugar has a mape error value of 24, and flour has a mape error value of 26.1. Furthermore, the raw material decomposition method for shrimp heads has a mape error value of 15, sugar has a mape error value of 15, and flour has a mape error value of 16.42. The second result of forecasting shows that the decomposition method obtains a smaller mape value or the lowest error value. This research also uses the Economic Order Quantity (EOQ) method in the 2022-2023 period with raw material yields of 515.28 kg of shrimp heads, 488.54 kg of sugar and 188.09 kg of flour.

Menu Sales Prediction at Kiyo Café Using Machine Learning

This research evaluates the performance of the K-Nearest Neighbors (KNN) and Naïve Bayes algorithms in predicting raw material stock for Café Kiyo. The study encompasses six key stages, including preparation, literature review, data collection, data mining processing, results and discussion, and conclusion with recommendations. The data mining process adheres to the Knowledge Discovery in Databases (KDD) framework, involving data selection, preprocessing, transformation, data mining, and interpretation and evaluation. The evaluation metrics reveal that KNN boasts a marginally higher accuracy of 98.71% compared to Naïve Bayes with 98.21%. KNN also demonstrates superior precision (81.25%) in identifying true positives, outperforming Naïve Bayes (72.59%). However, Naïve Bayes excels in recall, achieving 95.15% compared to KNN's 50.00%. The Area Under the Curve (AUC) analysis further confirms Naïve Bayes' superiority, with an AUC value of 0.995, indicating better performance in distinguishing between positive and negative classes.

Prediction of Bread Raw Material Stock At Al-Fattah Bakery and Cake Aek Teluk Kiri using SMA method

AL- Fattah Bakery and Cake is a company engaged in the production and sale of pastries. In managing raw material inventory, you must ensure sufficient inventory for sales, minimizing the time and costs required. Inventory control is an effort carried out by a company to optimize sales and seek as little risk as possible. The problem faced by AL- Fattah Bakery and Cake for each branch in Asahan Regency is the difficulty in determining the amount of raw material inventory that must be produced in the following month in order to continue to meet customer demand and not cause accumulation over a long period of time and maintain the stability of raw material stock. . Because if there is a buildup of stock, it could result in the product expiring and failing to be distributed to customers. This is caused by customer demand which changes every month following existing trends. The aim of this research is to predict raw material supplies using the SMA (Single Moving Average) method at AL- Fattah Bakery and Cake for each branch in Asahan Regency. Based on the results of the research that has been carried out, the Single Moving Average (SMA) method can help AL- Fattah Bakery and Cake Aek Teluk Kiri with the Single Moving Average Method in predicting the supply of bread raw materials for the following month.

Analysis and Design of Enterprise Architecture in The Implementation of Digital Transformation at Village Tourism of Kampung Patin Kampar Regency using TOGAF

The development of information technology helps the community, entrepreneurs and MSMEs. This research was conducted in Kampung Patin, Kampar Regency. This research aims to create an Enterprise Architecture (EA) TOGAF design for MSMEs in Kampung Patin, we all know this digital transformation is useful in increasing the business value of the surrounding economy. there is a special implementation in utilizing this role, building financial applications, raw material stock applications because these MSMEs are able to produce 34,000 tons to 45,000 tons of catfish every month. The processing of catfish is like regional souvenirs, namely: catfish meatballs, catfish nuggets, catfish batagor, catfish fillets, and catfish skin crackers. innovation like this alone is not enough to require technology and digital transformation in running a business and promoting processed catfish. the results of the study were designed in the form of an enterprise architecture blueprint for UMKM Kampung Patin as an internal guidebookincrease the effectiveness and efficiency of digital transformation in these MSMEs

ESG ratings and stock performance in the internet industry

Amidst the escalating emphasis on sustainable development, numerous corporations and organizations have intensified their environmental, social, and governance (ESG) efforts. The internet sector, intrinsically linked to the ESG domain, has consequently garnered amplified scrutiny. This study delves into the correlation between ESG ratings and the stock performance of publicly listed Chinese companies in the internet sector from 2016 to 2020. The findings reveal that initiatives in the ESG sphere significantly and negatively influence stock performance in these firms, assessed through raw stock returns, stock excess returns relative to the market index, Jensen’s one-factor alpha, and the Fama-French three-factor alpha. This inverse correlation between ESG ratings and stock performance is nonlinear and convex, indicating a lessening negative impact at elevated ESG levels. Moreover, this adverse effect is more pronounced in value stocks compared to growth stocks. Predominantly manifesting before 2018, this negative trend diminishes amidst the COVID-19 period. The reverse causality analysis employing lagged ESG ratings suggests that higher ESG ratings precipitate reduced stock performance, as opposed to vice versa. This study bridges a gap in the existing literature concerning ESG and stock performance specific to the Chinese internet industry and proposes recommendations for its sustainable evolution. AcknowledgmentThis research was supported by the Department of Education of Zhejiang Province General Program (Y202249981, Y202353438), the Wenzhou Association for Science and Technology – Service and Technology Innovation Program (jczc0254), the Wenzhou-Kean University Student Partnering with Faculty Research Program (WKUSPF2023004), the Wenzhou-Kean University International Collaborative Research Program (ICRP2023002, ICRP2023004), and the Wenzhou-Kean University Internal Research Support Program (IRSPG202205, IRSPG202206).

Perfluoroalkyl-Decorated Noble-Metal-Free MOFs for the Highly Efficient One-Pot Four-Component Coupling between Aldehydes, Amines, Alkynes, and Flue Gas CO2.

The non-noble-metal catalysed-multicomponent reactions between flue gas CO2 and cheap industrial raw stocks into high value-added fine chemicals is a promising manner for the ideal CO2 utilization route. To achieve this, the key fundamental challenge is the rational development of highly efficient and facile reaction pathway while establishing compatible catalytic system. Herein, through the stepwise solvent-assisted linker installation, post-synthetic fluorination and metalation, we report the construction of a series of perfluoroalkyl-decorated noble-metal-free metal-organic frameworks (MOFs) PCN-(BPY-CuI)-(TPDC-Fx ) [BPY=2,2'-bipyridine-5,5'-dicarboxylate, TPDC-NH2 =2'-amino-[1,1':4',1''-terphenyl]-4,4''-dicarboxylic acid] that can catalyze the one-pot four-component reaction between alkyne, aldehyde, amine and flue gas CO2 for the preparation of 2-oxazolidinones. Such assembly endows the MOFs with superhydrophobic microenvironment, superior water resistance and highly stable catalytic site, leading to 21 times higher turnover numbers than that of homogeneous counterparts. Mechanism investigation implied that the substrates can be efficiently enriched by the MOF wall and then the adsorbed amine species act as an extrinsic binding site towards dilute CO2 through their strong preferential formation to carbamate acid. Moreover, density functional theory calculations suggest the tetrahedral geometry of Cu in MOF offers special resistance towards amine poisoning, thus maintaining its high efficiency during the catalytic process.

Perfluoroalkyl‐Decorated Noble‐Metal‐Free MOFs for the Highly Efficient One‐Pot Four‐Component Coupling between Aldehydes, Amines, Alkynes, and Flue Gas CO2

AbstractThe non‐noble‐metal catalysed‐multicomponent reactions between flue gas CO2 and cheap industrial raw stocks into high value‐added fine chemicals is a promising manner for the ideal CO2 utilization route. To achieve this, the key fundamental challenge is the rational development of highly efficient and facile reaction pathway while establishing compatible catalytic system. Herein, through the stepwise solvent‐assisted linker installation, post‐synthetic fluorination and metalation, we report the construction of a series of perfluoroalkyl‐decorated noble‐metal‐free metal–organic frameworks (MOFs) PCN‐(BPY‐CuI)‐(TPDC‐Fx) [BPY=2,2′‐bipyridine‐5,5′‐dicarboxylate, TPDC‐NH2=2′‐amino‐[1,1′:4′,1′′‐terphenyl]‐4,4′′‐dicarboxylic acid] that can catalyze the one‐pot four‐component reaction between alkyne, aldehyde, amine and flue gas CO2 for the preparation of 2‐oxazolidinones. Such assembly endows the MOFs with superhydrophobic microenvironment, superior water resistance and highly stable catalytic site, leading to 21 times higher turnover numbers than that of homogeneous counterparts. Mechanism investigation implied that the substrates can be efficiently enriched by the MOF wall and then the adsorbed amine species act as an extrinsic binding site towards dilute CO2 through their strong preferential formation to carbamate acid. Moreover, density functional theory calculations suggest the tetrahedral geometry of Cu in MOF offers special resistance towards amine poisoning, thus maintaining its high efficiency during the catalytic process.