- Sample Financial Events:
| Reference | Paper | Data Source | Model | Evaluation Metric(s) | Time Period | Contributions | Venue |
|---|---|---|---|---|---|---|---|
| Geng et al. (2015) | Prediction of financial distress: An empirical study of listed Chinese companies using data mining | China, CSMAR | NN, DT, SVM, MV | Accuracy, Recall, Precision | 2001–2008 | phenomenon of financial distress for 107 Chinese companies that received the label‘special treatment’ from 2001 to 2008 by the Shanghai Stock Exchange and the Shenzhen Stock Exchange | Accounting |
| Liang et al. (2016) | Financial ratios and corporate governance indicators in bankruptcy prediction: A comprehensive study | Taiwan Economic Journal (TEJ) | SVM, KNN, NB, CART, MLP | ROC, Accuracy | 1999–2009 | assess the prediction performance obtained by combining seven different categories of FRs and five different categories of CGIs | Accounting, market, corporate governance |
| Olson et al. (2012) | Comparative analysis of data mining methods for bankruptcy prediction | USA, Compustat | DT, logit, MLP, RBFN, SVM | MSE | 2005–2009 | Research bankruptcy data and predict bankruptcy through information | Accounting |
| Ioannidis et al. (2010) | Assessing bank soundness with classification techniques | Bankscope, World Bank | UTADIS, MLP, CART, KNN, Ordered logit, stacked models | Accuracy | 2007–2008 | Use stack model to build bank warning model | Accounting, country-level variables |
| Boyacioglu et al. (2009) | Predicting bank financial failures using neural networks, support vector machines and multivariate statistical methods: A comparative analysis in the sample of savings deposit insurance fund (SDIF) transferred banks in Turkey | Turkey, Banks Association of Turkey | NN, SVM, MDA, K-means cluster analysis, logit | Using PCA, initial Eigenvalues | 1997–2004 | Use financial ratio as a predictor variable to establish a regression prediction model to predict bank failure probability | Accounting |
| Cecchini et al. (2010) | Making words work: Using financial text as a predictor of financial events | USA, Compustat, CRSP | SVM | Using defined Concept score | 1994–1999 | Develop a methodology for automatically analyzing text to aid in discriminating firms that encounter catastrophic financial events | MD&A, Altman variables |
| Kim et al. (2010) | Ensemble with neural networks for bankruptcy prediction | Korea | MLP + bagging, MLP + boosting | Predictive Accuracy, Predictive error rate | 2002–2005 | An ensemble with neural network for improving the performance of traditional neural networks on bankruptcy prediction tasks | Accounting |
| Mai et al. (2018) | Deep learning models for bankruptcy prediction using textual disclosures | USA, CRSP | CNN | AUC | 1994-2014 | Deep learning models for corporate bankruptcy forecasting using textual disclosures | Accounting |
| Snow et al. (2020) | Investigating Accounting Patterns for Bankruptcy and Filing Outcome Prediction using Machine Learning Models | USA, UCLA BRD | XGBClassifier | ROC, AUC | 1977-2016 | A modern gradient boosting machine (GBM), XGBoost, to predict litigated bankruptcies and filing outcomes | Accounting |
| Snow et al. (2020) | Predicting Global Restaurant Facility Closures | USA, Yelp | LightGBM | ROC | 2006-2017 | Through text mining and sentiment analysis, make survival predictions for restaurants | Accounting |
| Mohammad et al. (2020) | The Automated Venture Capitalist: Data and Methods to Predict the Fate of Startup Ventures | 2015 Massachusetts Institute of Technology $100K Launch competition (open sourced) | NN | AUC | / | Investigate how the composition of early-stage start-up teams, and the properties of their ventures, predict their nomination to a premier entrepreneurship competition, and their continued operation two years following | Accounting |
| Martin et al. (2013) | Bankruptcy prediction for small- and medium-sized companies using severely imbalanced datasets | / | SVM, IF | Accuerary | 2010-2016 | Unbalanced data sources | Accounting |
| Reference | Paper | Data Source | Model | Evaluation Metric(s) | Time Period | Contributions | Venue |
|---|---|---|---|---|---|---|---|
| Cristóbal et al. (2012) | Predicting IPO Underpricing with Genetic Algorithms | USA, AMEX, NASDAQ and NYSE IPOs | Genetic algorithms | RMSE, Precision | 1999-2010 | A rule system to predict first-day returns of initial public offerings based on the structure of the offerings | Accounting |
| Zhe et al. (2019) | NLP Driven Large Scale Financial Data Analysis | USA, Intrinio, The Reuters dataset | HAN | Accuracy | 2006-2013 | Explores the influence of various factors on the performance of utilizing NLP knowledge to predict stock trend of a company | Accounting |
| Jie et al. (2015) | Text Mining for Studying Management’s Confidence in IPO Prospectuses and IPO Valuations | USA, US SEC’s EDGA, CRSP | FOCAS-IE | Confusion Metrics, Accuracy | 2003-2013 | By analyzing MD&A, build an analysis framework FOCAS-IE, extract emotions, and use the information extracted by FOCAS-IE to build a predictive model | Accounting |
| David et al. (2015) | Fuzzy Techniques for IPO Underpricing Prediction | USA, National Association Of Securities Dealers | Rule-based | RMSE | 1999-2010 | Rule-based classification | Accounting |
| Reference | Paper | Data Source | Model | Evaluation Metric(s) | Time Period | Contributions | Venue |
|---|---|---|---|---|---|---|---|
| Adesoji et al. (1999) | Predicting Mergers and Acquisitions in the Food Industry | USA, SDC Platinum | Logit Models | Accuracy of 74.5% | 1985–1995 | Explain merger and acquisition (M&A) activities in US food manufacturing using firm level data for public firms | Food industry |
| Liu et al. (2007) | Financial Characteristics and Prediction on Targets of M&A Based on SOM-Hopfield Neural Network | China, Securities Journals, Web | Hopfield Network | STD. Error Mean | 2004-2006 | Apply self-organized mapping (SOM) and Hopfield neural network to cluster and predict the target of mergers and acquisitions | Accounting |
| Chin-Sheng et al. (2014) | Exploiting Technological Indicators for Effective Technology Merger and Acquisition (M&A) Predictions | USA, SDC Platinum | Ensemble | Accuracy, AUC, Recall, Precision, F1 | 1997–2008 | Propose a technology M&A prediction technology that takes technical indicators as independent variables and considers the technical profile of bidders and candidate target companies | Accounting |
| B.Shao et al. (2018) | Categorization of Mergers and Acquisitions in Japan Using Corporate Databases: A Fundamental Research for Prediction | Tokyo, UZABASE | Clustering | t-SNE visualization, Accuracy | 2003-2016 | Use M&A data, financial data and company data for M&A analysis | Accounting |
| Ye et al. (2011) | Board connections and M&A transactions | USA, SDC Platinum | Logit Models | ACAR, TCAR, PCAR | 1996–2008 | We examine M&A transactions between firms with current board connections and find that acquirers obtain higher announcement returns in transactions with a first-degree connection where the acquirer and the target share a common director | Accounting |
| Ryan et al. (2019) | Deal or No Deal: Predicting Mergers and Acquisitions at Scale | USA, EDGAR | Clustering | ROC, AUC, LDA | 1994-2018 | We utilize natural language processing (NLP) techniques to vectorize each filing’s textual data. Next, we cluster firms by industry and identify keywords suggestive of upcoming M&A activity. We then train a classifier to predict acquirers and targets, which we use to forecast the most likely M&As of 2019. Lastly, we deploy an application which enables users to query our forecasts and visualize our data | Accounting |
| Yang et al. (2020) | Generating Plausible Counterfactual Explanations for Deep Transformers in Financial Text Classification | U.S. Listed Companies | Transformers (BERT, RoBERTa), Adversarial Training, Counterfactual Explanations | MSE | 2007-2019 | Predict the results of a possible M&A deadls. Explain the prediction results by generating the plausible counterfactual explanations. | CoLING-20 |
| Philip et al. (2018) | Predictive Power? Textual Analysis in Mergers & Acquisitions | / | Linear Regression | Accuracy | 2002-2014 | M&A prediction using sentiment analysis | Accounting |