Regression and Machine Learning Methods to Predict Discrete Outcomes in Accounting Research

Abstract

Predictive modeling focuses on iteratively trying various combinations and transformations of a set of variables to generate a decision rule that predicts outcomes for new observations. Although accounting researchers have demonstrated interest in predictive modeling, we identify a lack of applied guidance on this topic for accounting settings. This issue has become more salient with the increasing availability of machine learning models that use unfamiliar terminology, are estimated using algorithms, and produce different outputs than other models used for causal inference. To overcome this gap, we provide an overview of how to predict discrete outcomes with logistic regression and machine learning models use in recent studies. We also include guidance and a comprehensive example – predicting investigations by the U.S. Securities and Exchange Commission – that illustrates the elements of the prediction process, highlighting the importance of out-of-sample accuracy and unique aspects in the presentation of a prediction model’s results.

Exploring visual communication in corporate sustainability reporting: Using image recognition with deep learning

“…The original materials for this analysis were shown in Chapter 14 of Nakao et al (2023) and Table A1 and Table 2. 3 Some accounting and organisational research studies have employed machine learning (Fieberg et al, 2022;Hannigan et al, 2019;Hu & Sun, 2022;Krupa & Minutti-Meza, 2022;Velte, 2023) We then identify the detected faces by gender (men or women), and we categorise the age groups as follows: 0-10 years as 'children', The descriptive statistics for face detection in Amazon Rekognition show more men than women, a predominant 'middle-aged' group, 33% smiles and 10% beards, marking the first detailed study on facial images in sustainability reporting. Table A2 provides further details on the descriptive statistics.…”

BAT inspired regression model for prediction of power loss in solar panel

“…Regression analysis seeks to develop a mathematical formula that, given the values of the independent variables, can precisely predict the value of the dependent variable. [32,33].…”