•We introduce two heterogeneous hypergraphs to separately characterize the groupwise relationships of industry-belonging and fund-holding among stocks. To the best of our knowledge, we are the first ...to leverage both the group-wise relationships of industry-belonging and fund-holding relationships for stock trend prediction.•We propose a novel hypergraph tri-attention network (HGTAN) that consists of hierarchical attention modules to consider the importance of different nodes, hyperedges, and hypergraphs when guiding the information propagation in stock hypergraphs.•We conduct both experimental evaluation and investment simulation on real-world data, and the results demonstrate the validity and rationality of our approach.
Predicting the future price trends of stocks is a challenging yet intriguing problem given its critical role to help investors make profitable decisions. In this paper, we present a collaborative temporal-relational modeling framework for end-to-end stock trend prediction. Different from existing studies relying on the pairwise correlations between stocks, we argue that stocks are naturally connected as a collective group, and introduce two heterogeneous hypergraphs to separately characterize the stock group-wise relationships of industry-belonging and fund-holding. A novel hypergraph tri-attention network (HGTAN) is proposed to augment the hypergraph convolutional networks with a hierarchical organization of intra-hyperedge, inter-hyperedge, and inter-hypergraph attention modules. In this manner, HGTAN adaptively determines the importance of nodes, hyperedges, and hypergraphs during the information propagation among stocks, so that the potential synergies between stock movements can be fully exploited. Experimental evaluation and investment simulation on real-world stock data demonstrate the effectiveness of our approach.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Combining the existing safety input data and characteristics, this paper uses the dynamic change method to solve the safety input problem. The origin, flow and characteristics of safety investment ...are analyzed, the skills of system dynamics modelling and the simulation modeling software Vensim are used to build the model, including models of safety precaution, safety control and accident risk transfer etc. Through simulation modeling, the configuration effects under different configuration schemes in an enterprise are completely decomposed. The results show that the effects of different configuration schemes on accident frequency, loss value and total accidents counts be obtained by applying the model built, which has great positive significance and practical value for dynamic safety investment.
Manufacturers have to look constantly for new strategies and tools to improve processes, decrease cost and increase productivity and efficiency. Production scheduling is one of the crucial elements ...in manufacturing and has an impact on delivery deadlines and also on the production process in terms of its utilization. On the other hand, the value stream optimization is very important for lean manufacturing efforts. This paper is aimed to research the impact of job shop scheduling on value stream optimization and decreasing of cost-time investment. Value stream mapping represents a very efficient tool for visualization of activities within production flow focused on activity duration with the purpose to eliminate non-value added activities. Value stream costing is based on value stream and eliminates the need for overhead allocation and calculation. Cost-time profile is a powerful tool for visualization and calculation of cost accumulation during the time across the entire manufacturing flow. Software tools used in this paper are: Lekin scheduling system for constructing the schedules based on four different dispatching rules and Cost-Time Profiler software for simulating the impact of different schedules on total production cost and cost-time investment (representing the time value of money), which is proposed as a new scheduling objective function.
Full text
Available for:
IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
This paper provides a view on the cyclicality of capital-intensive industries that could add considerably to our understanding of how cycles in prices, profits and capacity come about. Previous ...studies of business cycles focus on macro-economic systems or on the agricultural sector. Causes for fluctuations are typically believed to be mainly exogenous in nature. We seek to extend the existing literature on industrial cycles by developing a model that incorporates endogenously generated cyclicality. A simulation model of the paper industry is developed, and validated on the basis of data for the US paper industry.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK
Much research in recent years has focused on stock price prediction. In previous research learning data of a prediction target company is used. However, there is not learning data for the prediction ...target company often in the real world. In this research existing data of other companies is used as learning data based on Bayesian statistics. In previous research deep learning by fully connected neural networks is applied to predict stock price. In this research deep learning by fully connected neural networks based on Bayesian statistics is applied to predict stock price. This research is one of the extended research of the previous research from the viewpoint of Bayesian statistics. A new prediction method is proposed. Results of some stock price prediction experiments and investment simulations are shown. The effectiveness of the proposed method is shown by the results of the investment simulations.
This chapter analyzes the pitfalls to avoid and present a framework for interpreting results. Regression analysis is the main tool used by statisticians to uncover a linear relationship between two ...or more variables. The risk for a quantitative investor's discovering an apparently strong relationship between a factor and subsequent returns is that the relationship is not real but a false positive found through data mining. It is possible, given a large enough body of data, to find relationships between variables that are merely the result of random chance. The objective of this chapter is to develop a sensible quantitative value investment strategy that will deliver returns in the real world. Simpler models have fewer and more concrete rules, and thus, tend to be more robust. Complex models have more rules, which are more intuitive and open to interpretation. One of the reasons that quantitative investing works well is that it prompts the investor to crystallize at the outset the means by which he or she will analyze a stock.
This paper assesses the impact of a decision support system (DSS), the Investment Simulation Model (ISM), on recommendations given by extension officers to pig farmers. ISM gives insight into the ...relation between strategic investment decision rules and their simulated outcome. An evaluation procedure was developed testing ISM under operational use. The model was put to the test on three farms and with three extension officers. For each farm, three sets of recommendations were prepared: (1) without using ISM, based on a farm visit to collect data; (2) with use of ISM, based on a farm visit to collect data; and (3) with use of ISM, but with data collected by another advisor. The field test resulted in striking differences between recommendations based on ISM and those not based on ISM. In the latter recommendations, immediate farm expansion was regarded as not feasible for two of the three farms. When using ISM, a farm expansion strategy was advised for all three farms, however, not immediately. Without using ISM, replacement strategies for the buildings, manure costs, and family expenditures were largely ignored in the advice, contrary to the advice based on ISM. Adjusted for the difference in travelling time, the time required for preparing advice using ISM equaled 80% of the time required for preparing advice not using ISM. Whether or not the extension officer himself collected the farm data did not influence the advice.
Full text
Available for:
IJS, IMTLJ, KILJ, KISLJ, NUK, SBCE, SBJE, UL, UM, UPCLJ, UPUK
The author describes how investment research workshops were used to prepare students at Texas A&M University (TAMU) to compete in the 2008 Equitrader Collegiate Challenge. The Equitrader Collegiate ...Challenge is a simulated equity trading competition that enables students to match wits against the market and other contestants. This paper describes an interactive approach to investment literacy, which guided students through a logical process of utilizing professional-level investment resources, such as Morningstar and Thomson One Banker, to conduct investment research and analysis for stock selection.
This paper identifies a subset of emerging markets that have higher than average expected returns and studies risk properties of this subset by investment simulations. It is found that: (1) the ...portfolio of ‘value’ emerging markets generates superior returns; and (2) statistical measures of its risk are close to the corresponding measures for the portfolio of all emerging markets. The statistical significance of these results has been checked by a bootstrap procedure. The results imply that the optimal share of emerging markets increases from 0% for an equally weighted portfolio to approximately 25% for the portfolio of undervalued emerging markets.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK