Advances in Business and Management Forecasting: Volume 14

The purpose of this study is to determine which quantitative metrics are most representative of investor sentiment in the US equity markets. Sentiment is the aggregation of consumers', investors', and producers' thoughts and opinions about the future of the financial markets. By analyzing the change in popular economic indicators, financial market statistics, and sentiment reports, we can gain information on investor reactions. Furthermore, we will use machine learning techniques to develop predictive models that will attempt to forecast whether the stock market will go up or down based on the percent change in these indicators.

This chapter concerns itself with the development of a regression model for an executive compensation forecasting of the top-level executives of MetLife. The data observations consist of a list of 12 comparable corporations selected from comparable financial institutions. A set of 28 financial variables from each of the corporations is compiled as the data source of this regression model.

The objective of this research is to develop a model to forecast sales for an ice-cream company. In order to achieve this objective, we evaluate sales data of three ice-cream flavors namely vanilla, chocolate, and Tally Ho (mixture of chocolate and vanilla) from January 2016 to 25 November 2019. To determine which model worked the best, we tested different models such as moving averages, simple exponential smoothing, Holt's method, Winters' method, method modeling seasonality and trend, and an ensemble method. We found Winters' method and modeling seasonality and trend performed well in terms of lowest error rates compared with other methods.

Predicting a patient's length of stay (LOS) in a hospital setting has been widely researched. Accurately predicting an individual's LOS can have a significant impact on a healthcare provider's ability to care for individuals by allowing them to properly prepare and manage resources. A hospital's productivity requires a delicate balance of maintaining enough staffing and resources without being overly equipped or wasteful. This has become even more important in light of the current COVID-19 pandemic, during which emergency departments around the globe have been inundated with patients and are struggling to manage their resources.

In this study, the authors focus on the prediction of LOS at the time of admission in emergency departments at Rhode Island hospitals through discharge data obtained from the Rhode Island Department of Health over the time period of 2012 and 2013. This work also explores the distribution of discharge dispositions in an effort to better characterize the resources patients require upon leaving the emergency department.

We study the performances of various predictive models including decision trees, random forests, neural networks, and linear discriminant analysis on an imbalanced data set of home loan applications. During the process, we propose our undersampling algorithm to cope with the issues created by the imbalance of the data. Our technique is shown to work competitively against popular resampling techniques such as random oversampling, undersampling, synthetic minority oversampling technique (SMOTE), and random oversampling examples (ROSE). We also investigate the relation between the true positive rate, true negative rate, and the imbalance of the data.

In a previous chapter (Klimberg, Ratick, & Smith, 2018), we introduced a novel approach in which cluster centroids were used as input data for the predictor variables of a multiple linear regression (MLR) used to forecast fleet maintenance costs. We applied this approach to a real data set and significantly improved the predictive accuracy of the MLR model. In this chapter, we develop a methodology for adjusting moving average forecasts of the future values of fleet service occurrences by interpolating those forecast values using their relative distances from cluster centroids. We illustrate and evaluate the efficacy of this approach with our previously used data set on fleet maintenance.

A majority of products for manufacturing or consumers have multiple characteristics that must meet the requirements of the customer. For example, a steel beam any have dimensional tolerances on its length, width, or height and functional tolerances on its strength. The characteristics are influenced by different processes that create the product. For an individual characteristic, process capability measures exist that convey the degree to which the characteristic meets the specification requirements. Such measures may indicate the proportion of nonconforming product related to the particular characteristic, under some distributional assumptions of the characteristic. For products with multiple characteristics, the unit costs of rectification may be different, making the satisfaction of some characteristics meeting customer requirements more important than others. In this paper, an aggregate process capability performance measure is developed that considers the relative importance of the characteristic based on unit costs of nonconformance. Based on the aggregate measure, appropriate process capability measures for the individual measures are also derived. Bounds on the aggregate capability measures are also established.

Product success is contingent on forecasting when a product is needed and how it should be offered. Forecasting accuracy is contingent on the correct forecasting technique. Using supermarket data across two product categories, this chapter shows that using a bevy of forecasting methods improves forecasting accuracy. Accuracy is measured by the mean absolute percentage error. The optimal methods for one consumer goods product may be different than for another. The best model varied from sophisticated, most such as autoregressive integrated moving average (ARIMA) and Holt–Winters to a random walk model. Forecasters must be proficient in multiple statistical techniques since the best technique varies within a categories, variety, and product size.

In China, more than 80,000 people have been diagnosed with COVID-19, and more than 3,000 people have lost their lives. It seems that there will be more deaths since the epidemic is not over. All the Chinese provinces have reported the COVID-19 cases. This chapter aims to explore the trend of COVID-19 treatment efficiency in Chinese provinces using the data released daily by China Center for Disease Control and Prevention. Since China Center for Disease Control and Prevention began to release data daily from January 24 to March 12, we have more than 40 groups of daily data for 31 provinces in China mainland. In the calculation, we take the daily data of each province as a sample and then we have more than 1,200 samples in this study.

We use additive two-stage data envelopment analysis as an efficiency evaluation tool to calculate the COVID-19 treatment efficiency. In our framework, the first stage is to understand the infection rate and the second stage is to evaluate the treatment efficiency. In the first stage for the tth day, we use total population (p) and number of people infected in the previous day (inf _t−1) as the inputs and cumulative number of people infected in the current day (inf _t ) as the output. In the second stage for the tth day, we use cumulative number of people infected in the current day (inf _t ) as the input and cumulative death in the current day (death _t ) and cumulative recovery in the current day (recov _t ) as the outputs. Some techniques on how to deal with undesirable outputs such as inf _t and death _t are employed in this study.

After we have the infection rate and treatment efficiency for the samples more than 1,200, we analyze the COVID-19 treatment efficiency and its development trend from January 24 to March 12 in 34 regions of China from static and dynamic aspects. The results show that, on the whole, the overall efficiency and phased efficiency of COVID-19 treatment efficiency in all regions of China are relatively high, which reflects the key factor for the Chinese government to quickly control the epidemic in the short term. Relatively speaking, the average efficiency value in the infection stage (first stage) is lower than the average efficiency value in the healing stage (second stage), which shows that the focus of anti-epidemic in China should be early detection and prevention rather than treatment process. In terms of trend, the total efficiency of COVID-19 treatment in each region shows a trend of “increasing first and then decreasing.” Our analysis indicates that in the initial stage, the continuous increase of various resources leads to the rise of the total efficiency, while in the later stage, the rapid decline of the number of infected people leads to the decrease of the total efficiency. Based on the results of the efficiency analysis, this study provides corresponding management implications and policy suggestions, hoping to provide some enlightenment and suggestions for the anti-epidemic work of other countries in the severe environment where the epidemic is spreading rapidly.

The tension between the United States and China has not ended, despite the lengthy negotiations carried out in 2019 to appease differences and decrease protectionism over the technology industry, since the trade war was producing devastating consequences for both powers and international trade. The resurgence of tension is due to two main factors, such as mutual accusations about who is to blame for the origin of COVID-19 and the use of the new 5G mobile technology by Chinese companies like ZTE and Huawei. We developed an in-depth analysis of the consequences on international prices of the technology industry and international trade due to the reappearance of the trade conflict between China and the United States. This analysis will be carried out through the application of economic theories. There is greater distrust in the technology sector, and this produces a variation in the price of the technology industry. Likewise, according to Marshall's law of demand and supply, this effect can be explained more accurately; since there was a lower demand for technological products, the digital industry will have to lower its prices to generate income.

The following chapter aims to investigate the impact on the prices of inferior goods from COVID-19, a global pandemic with a spread never before seen, and in order to stipulate the possible consequences, a contrast was made with past world crises in order to speculate the state in which the country and its citizens would be economically benefited. The chapter has been based on articles previously carried out by specialists, said essays, likewise, that have been contrasted by different authors; therefore, it could be stipulated that the methodology used throughout the trial was the one applied, since it was based on prior knowledge from great scholars on the subject. The results found indicate that, even though the country is in an uncertain outlook, the possibilities of economic recovery are high since previous economic crises denote large drops in money fluctuation with a high rate of recovery.