Search results

Accounting information systems are mainly rule-based, and data are usually available and well-structured. However, many accounting systems are yet to catch up with current technological developments. Thus, artificial intelligence (AI) in financial accounting is often applied only in pilot projects. Using AI-based forecasts in accounting enables proactive management and detailed analysis. However, thus far, there is little knowledge about which prediction models have already been evaluated for accounting problems. Given this lack of research, our study aims to summarize existing findings on how AI is used for forecasting purposes in financial accounting. Therefore, the authors aim to provide a comprehensive overview and agenda for future researchers to gain more generalizable knowledge.

The authors identify existing research on AI-based forecasting in financial accounting by conducting a systematic literature review. For this purpose, the authors used Scopus and Web of Science as scientific databases. The data collection resulted in a final sample size of 47 studies. These studies were analyzed regarding their forecasting purpose, sample size, period and applied machine learning algorithms.

The authors identified three application areas and presented details regarding the accuracy and AI methods used. Our findings show that sociotechnical and generalizable knowledge is still missing. Therefore, the authors also develop an open research agenda that future researchers can address to enable the more frequent and efficient use of AI-based forecasts in financial accounting.

Owing to the rapid development of AI algorithms, our results can only provide an overview of the current state of research. Therefore, it is likely that new AI algorithms will be applied, which have not yet been covered in existing research. However, interested researchers can use our findings and future research agenda to develop this field further.

Given the high relevance of AI in financial accounting, our results have several implications and potential benefits for practitioners. First, the authors provide an overview of AI algorithms used in different accounting use cases. Based on this overview, companies can evaluate the AI algorithms that are most suitable for their practical needs. Second, practitioners can use our results as a benchmark of what prediction accuracy is achievable and should strive for. Finally, our study identified several blind spots in the research, such as ensuring employee acceptance of machine learning algorithms in companies. However, companies should consider this to implement AI in financial accounting successfully.

To the best of our knowledge, no study has yet been conducted that provided a comprehensive overview of AI-based forecasting in financial accounting. Given the high potential of AI in accounting, the authors aimed to bridge this research gap. Moreover, our cross-application view provides general insights into the superiority of specific algorithms.

The purpose of this paper is to investigate the initiation of accounting information system projects. Specifically, it examines the role of the predictive analytics (PA) project initiator in the integration of financial and operational sales forecasts.

The study uses a field study method to address the studied phenomenon in eight Finnish companies that have recently adopted PA systems. The data are primarily based on 19 interviews in the companies and five interviews with the PA consultants.

The authors found that initiators appear to play a major role regarding the degree of integration of financial and operational sales forecasts. The initiators from an accounting function have a tendency to pay more attention to the integration than the representatives from other functions, such as operations and sales.

The study also makes a practical contribution to companies in showing and discussing the important role of the accounting department as an initiator of a project if the target is to achieve a tight coupling of financial and operational forecast figures, i.e., “one set of numbers”.

Even though companies have increasingly adopted PA systems in recent years, we still know little about how the initiation affects the design of accounting information systems overall. The central contribution of the paper, therefore, is to show that if a PA project is initiated by the accounting department, data integration becomes more likely. It contributes also to the discussion related to the appropriateness of data integration in the context of forecasting.

More frequent re‐forecasting is becoming an important topic on corporate agendas and is seen by many to be the only way to keep financial performance on track at a time when revenues are becoming less predictable. The paper aims to investigate this topic.

For the past four years ALG Software has commissioned a study of the re‐forecasting practices in a sample of the top organisations in the UK by revenue. The objective of the study is to benchmark how frequently the UK's leading organisations currently re‐forecast and what their goals are for the future.

The results show that the majority of organisations remain dissatisfied with the frequency with which they re‐forecast and wish to re‐forecast more frequently. However, the findings also show that many organisations feel that they cannot re‐forecast as often or as quickly as they would like. In fact, evidence suggests that little, if any, progress has been made during the last four years since this survey was first commissioned. This is due to either the amount of time it takes operational line managers to re‐forecast their resource requirements, or the amount of time it takes the finance function to complete a round of re‐forecasting. The type of application used for budgeting and re‐forecasting appears to make little difference to the time it takes organisations to produce an annual budget or complete a re‐forecast. Central to this issue is the use of non‐financial or “operational” data that predicts future resource requirements, and the limitations of the budgeting systems that organisations currently employ. Regardless of the type of application used for budgeting or re‐forecasting, much of this modelling is still done off‐line on spreadsheets.

The paper is of value to finance managers considering choosing a new budgeting application who will need to ensure that the type of operational modelling of non‐financial driver data, currently done offline on spreadsheets by line managers, can be seamlessly integrated into the central budgeting model.

Presents a case study demonstrating financial statement ratio analysis (FSRA). This analysis matches company to industry data and builds sales forecasting models. FSRA imputes forecast standards of sales and costs, and applies them to a budgeted financial statement variance analysis for the EE (electronic and electrical) industry. Develops the concept of industry base standards, integrating them into the more traditional statistical and accounting concepts of quality control standards. Provides an implementation example, and reviews possible improvements to the current methodology and approach. Uses a similar methodology to forecast the stock market value with some exceptions. Models sales and costs of an individual company and an industry based largely on aggregate industry databases. For this purpose, uses a multivariate linear trend regression analysis for the sales forecasting model. Defines and tests related hypotheses and evaluates their significance and confidence levels. For an illustration uses the EE industry and the APM company. Also demonstrates a microcomputer‐based FSRA software that speeds, facilitates, and helps to accomplish the stated objectives. The FSRA software uses industry financial statement databases, computes financial ratios and builds forecasting models.

We propose a Machine Learning (ML) approach that will be trained from the available financial data and is able to gain the trends over the data and then uses the acquired knowledge for a more accurate forecasting of financial series. This work will provide a more precise results when weighed up to aged financial series forecasting algorithms. The LSTM Classic will be used to forecast the momentum of the Financial Series Index and also applied to its commodities. The network will be trained and evaluated for accuracy with various sizes of data sets, i.e. weekly historical data of MCX, GOLD, COPPER and the results will be calculated.

Desirable LSTM model for script price forecasting from the perspective of minimizing MSE. The approach which we have followed is shown below. (1) Acquire the Dataset. (2) Define your training and testing columns in the dataset. (3) Transform the input value using scalar. (4) Define the custom loss function. (5) Build and Compile the model. (6) Visualise the improvements in results.

Financial series is one of the very aged techniques where a commerce person would commerce financial scripts, make business and earn some wealth from these companies that vend a part of their business on trading manifesto. Forecasting financial script prices is complex tasks that consider extensive human–computer interaction. Due to the correlated nature of financial series prices, conventional batch processing methods like an artificial neural network, convolutional neural network, cannot be utilised efficiently for financial market analysis. We propose an online learning algorithm that utilises an upgraded of recurrent neural networks called long short-term memory Classic (LSTM). The LSTM Classic is quite different from normal LSTM as it has customised loss function in it. This LSTM Classic avoids long-term dependence on its metrics issues because of its unique internal storage unit structure, and it helps forecast financial time series. Financial Series Index is the combination of various commodities (time series). This makes Financial Index more reliable than the financial time series as it does not show a drastic change in its value even some of its commodities are affected. This work will provide a more precise results when weighed up to aged financial series forecasting algorithms.

We had built the customised loss function model by using LSTM scheme and have experimented on MCX index and as well as on its commodities and improvements in results are calculated for every epoch that we run for the whole rows present in the dataset. For every epoch we can visualise the improvements in loss. One more improvement that can be done to our model that the relationship between price difference and directional loss is specific to other financial scripts. Deep evaluations can be done to identify the best combination of these for a particular stock to obtain better results.

Earnings forecasts provide useful numerical information concerning the expectations of a firm's future prospects and indicate management's ability to anticipate a firm's changing internal structure and external environment. The reasons for studying the accuracy of earnings forecasts is due to the Securities and Exchange Commission's position on financial forecasts and the issuance of a Statement of Position by the AICPA. These statements are important since they, in part, have motivated researchers to the importance of forecasting financial information. Consequently, if the disclosure of earnings forecasts in financial reports is permissable, the improvement of financial forecasts should be one of the primary concerns of the AICPA, the SEC, and numerous other interested groups.

Fiscal stress has forced local governments to pay increasing attention to revenue trends and has increased the importance of financial forecasting in local government. After reviewing the role of revenue forecasting in financial planning and discussing the use of regression and econometric analysis in revenue forecasting, this article applies this technique to forecast several key revenue components in a medium-sized city. Three general conclusions may be drawn: (1) systematic revenue forecasting and long-range planning are necessities, not luxuries, (2) risk aversion to "technical" revenue forecasting can be overcome, and (3) the implementation of a systematic revenue forecasting system does not require a battery of "rocket scientists." As municipal revenue bases come to rely less on relatively stable property taxes and more on less stable sources such as sales taxes, fees, and charges, the use of a regression and econometric based model should prove increasingly fruitful.

Earnings forecasts provide useful numerical information concerning the expectations of a firm's future prospects and indicate management's ability to anticipate a firms changing internal structure and external environment. The accuracy of these earnings forecasts that has been given so much attention is due to the S.E.C.'s position on financial forecasts and the issuance of the Statement of Position by the AICPA. These statements are important since they, in part, have motivated researchers to the importance of forecasting financial information. Consequently, if the disclosure of earnings forecasts in financial reports is permissable, the improvement of financial forecasts should be one of the primary concerns of the AICPA, the SEC, and numerous other interested groups.

This paper aims to investigate the informativeness of rhetorical impression management patterns of CEO letters and examines whether these rhetorical features affect financial analysts’ forecasting behaviour.

The authors use textual analysis on a sample of 526 CEO letters of US firms and apply factor analysis on individual linguistic style measures to identify co-occurrence patterns of style features.

The authors identify three holistic style patterns (assertive acclaiming, cautious plausibility-based framing and logic-based rationalizing) and find that assertive rhetorical feature in CEO letters is negatively related with the dispersion of financial analysts’ earnings forecasts and positively associated with earnings forecast accuracy. CEOs’ use of a rationalizing rhetorical pattern tends to decrease the dispersion of financial analysts’ earnings, whereas a cautious plausibility-based rhetorical position is only marginally instrumental in getting more accurate earnings predictions.

Whilst impression management communication is often theorized as manipulative and void of real information content, the findings suggest that impression management serves both self-presentation and information-sharing purposes.

This paper elaborates on the co-occurrence of style characteristics in management communication and is a first attempt to validate the external ramifications of holistic style profiles of corporate narratives by focusing on an economic target audience.

The purpose of this paper is to test whether financial analysts’ rationality in making stocks’ earnings forecasts is homogenous or not across different information regimes in stocks’ past returns.

By treating stocks’ past returns as the information variable in this study, the authors employ a threshold regression model to capture and test threshold effects of stocks’ past returns on financial analysts’ rationality in making earnings forecasts in different information regimes.

The results show that three significant structural breaks and four respective information regimes are identified in stocks’ past returns in the threshold regression model. Across the four different information regimes, financial analysts react to stocks’ past returns quite differently when making one-quarter ahead earnings forecasts. Furthermore, the authors find that financial analysts are only rational in a certain information regime of stocks’ past returns depending on a certain return-window such as one-quarter, two-quarter or four-quarter time period.

This study is different from those in the existing literature by arguing that there could exist heterogeneity in financial analysts’ rationality in making earnings forecasts when using stocks’ past returns information. The finding that financial analysts react to stocks’ past returns differently in the different information regimes of past returns adds value to the research on financial analysts’ rationality.