Construction of Corporate Investment Decision Support Model Based on Deep Learning

Aiming at the problem of corporate investment decision support, this paper proposes and constructs a stock quality evaluation model based on deep learning and applies it to the stock quality evaluation of e-commerce enterprises. Firstly, LSTM neural network is used to construct the evaluation and prediction model. Secondly, the evaluation index system is constructed. Finally, the structure and parameters of the model are designed, and the prediction model is tested and evaluated through simulation experiments. The experiments prove that the model is reasonable and feasible, which can provide a reference for investors to make decisions.

The Use of RONA/WACC as a Proxy for Investment Quality

Proxies for stock investment quality have varied from multi-factor models such as the Piotroski F-Score to simple one-factor return on capital measures. Economic value added, measured as the ratio of return on net assets relative to the weighted average cost of capital, has not been used as a proxy for stock quality. The aim of this study was to demonstrate that economic value added can be used effectively as a proxy for stock quality. Industrial stocks listed on the JSE ALSI between 31 January 2006 and 31 December 2015 comprised the population of this study. Three portfolios (comprising 33% of the population each) were formed monthly and were held for 12 months leading to the creation of 360 portfolios. The portfolios were formed on the basis of the RONA/WACC ratio; stocks with the highest ratios comprised HEV portfolios, stocks with the lowest ratios comprised LEV portfolios and stocks with median ratios comprised MEV portfolios. HEV portfolios earned a mean return of 19.52% relative to 13.09% for MEV portfolios, 16.31% for LEV portfolios and 13.73% for the overall equity market. The maximum cumulative value of R1 invested in HEV portfolios was equal to R5.30 as at the end of the study period. The maximum cumulative value of R1 invested in MEV and LEV portfolios was equal to R4.14 and R4.40 respectively. The maximum corresponding value of R1 invested in the general equity market was, R3.50. The superior returns of HEV portfolios were observed to be more risk efficient relative to both MEV and LEV portfolios and relative to the market portfolio on the basis of higher Sharpe Ratios. The RONA/WACC ratio has thus been shown to have been an effective proxy for stock quality.

Using Nomograms for Evaluating Plant Morphological and Physiological Data

Simple, graphical techniques are available to plant professionals to evaluate morphological and physiological data. The most commonly used graphs show only one variable at a time. However, plotting two variables into a simple coordinate system and adding diagonal lines to show relationships between those two variables greatly enhances the interpretive possibilities available to the plant practitioner by facilitating simultaneous comparisons of multiple variables. This easy-to-use nomogram is useful for evaluating and comparing plant responses to treatments and environments, plant development over time, and stock quality among species, genotypes, and other factors. This article describes how to construct this type of graph, the kind of data for which this technique is most useful, and how it can be applied to operational and research activities.