Forecasting bank failures and stress testing: A machine learning approach

This paper presents a forecasting model of bank failures based on machine-learning. The proposed methodology defines a linear decision boundary that separates the solvent banks from those that failed. This setup generates a novel alternative stress-testing tool. Our sample of 1443 U.S. banks includes all 481 banks that failed during the period 2007–2013. The set of explanatory variables is selected using a two-step feature selection procedure. The selected variables were then fed to a support vector machines forecasting model, through a training–testing learning process. The model exhibits a 99.22% overall forecasting accuracy and outperforms the well-established Ohlson’s score.     

Fathoming empirical forecasting competitions’ winners

The M5 forecasting competition has provided strong empirical evidence that machine learning methods can outperform statistical methods: in essence, complex methods can be more accurate than simple ones. Regardless, this result challenges the flagship empirical result that led the forecasting discipline for the last four decades: keep methods sophisticatedly simple. Nevertheless, this was a first, and we can argue that this will not happen again. There has been a different winner in each forecasting competition. This inevitably raises the question: can a method win more than once (and should it be expected to)? Furthermore, we argue for the need to elaborate on the perks of competing methods, and what makes them winners?     

Preventing rather than punishing: An early warning model of malfeasance in public procurement

Is it possible to predict malfeasance in public procurement? With the proliferation of e-procurement systems in the public sector, anti-corruption agencies and watchdog organizations have access to valuable sources of information with which to identify transactions that are likely to become troublesome and why. In this article, we discuss the promises and challenges of using machine learning models to predict inefficiency and corruption in public procurement. We illustrate this approach with a dataset with more than two million public procurement contracts in Colombia. We trained machine learning models to predict which of them will result in corruption investigations, a breach of contract, or implementation inefficiencies. We then discuss how our models can help practitioners better understand the drivers of corruption and inefficiency in public procurement. Our approach will be useful to governments interested in exploiting large administrative datasets to improve the provision of public goods, and it highlights some of the tradeoffs and challenges that they might face throughout this process.     

Forecasting solar stock prices using tree-based machine learning classification: How important are silver prices?

Solar energy is one of the fastest growing sources of electricity generation. Forecasting solar stock prices is important for investors and venture capitalists interested in the renewable energy sector. This paper uses tree-based machine learning methods to forecast the direction of solar stock prices. The feature set used in prediction includes a selection of well-known technical indicators, silver prices, silver price volatility, and oil price volatility. The solar stock price direction prediction accuracy of random forests, bagging, support vector machines, and extremely randomized trees is much higher than that of logit. For a forecast horizon of between 8 and 20 days, random forests, bagging, support vector machines, and extremely randomized trees achieve a prediction accuracy greater than 85%. Although not as prominent as technical indicators like MA200, WAD, and MA20, oil price volatility and silver price volatility are also important predictors. An investment portfolio trading strategy based on trading signals generated from the extremely randomized trees stock price direction prediction outperforms a simple buy and hold strategy. These results demonstrate the accuracy of using tree-based machine learning methods to forecast the direction of solar stock prices and adds to the broader literature on using machine learning techniques to forecast stock prices.     

Are forecasting competitions data representative of the reality?

Forecasters typically evaluate the performances of new forecasting methods by exploiting data from past forecasting competitions. Over the years, numerous studies have based their conclusions on such datasets, with mis-performing methods being unlikely to receive any further attention. However, it has been reported that these datasets might not be indicative, as they display many limitations. Since forecasting research is driven somewhat by data from forecasting competitions, it becomes vital to determine whether they are indeed representative of the reality or whether forecasters tend to over-fit their methods on a random sample of series. This paper uses the data from M4 as proportionate to the real world and compares its properties with those of past datasets commonly used in the literature as benchmarks in order to provide evidence on that question. The results show that many popular benchmarks of the past may indeed deviate from reality, and ways forward are discussed in response.     

Nowcasting GDP using machine-learning algorithms: A real-time assessment

Can machine-learning algorithms help central banks understand the current state of the economy? Our results say yes! We contribute to the emerging literature on forecasting macroeconomic variables using machine-learning algorithms by testing the nowcast performance of common algorithms in a full ‘real-time’ setting—that is, with real-time vintages of New Zealand GDP growth (our target variable) and real-time vintages of around 600 predictors. Our results show that machine-learning algorithms are able to significantly improve over a simple autoregressive benchmark and a dynamic factor model. We also show that machine-learning algorithms have the potential to add value to, and in one case improve on, the official forecasts of the Reserve Bank of New Zealand.     

Ranking professional forecasters by the predictive power of their narratives

This article presents the first ever ranking of professional forecasters based on the predictive power of the narrative of their regular research reports. The ranking is generated by applying the fully automated four-step procedure – called NLP-ForRank – developed in this article. The four steps are data scraping from the internet; data preparation; application of the natural language processing (NLP) models; and evaluation of the predictive power of the NLP indexes with linear regression, Granger causality, vector autoregression (VAR), and random forest forecasting models. Applying this procedure to five large Polish banks and to many time series shows that including the constructed NLP indexes in the forecasting models lowers the forecast errors, and that the optimal model almost always contains the NLP index. The financial news agencies could consider publishing this type of ranking on a regular basis as it would foster accountability, transparency, and a more competitive environment in the professional forecasting industry.     

Forecasting football results and exploiting betting markets: The case of “both teams to score”

The continuous growth of available football data presents unprecedented research opportunities for a better understanding of football dynamics. While many research works focus on predicting which team will win a match, other interesting questions, such as whether both teams will score in a game, are still unexplored and have gained momentum with the rise of betting markets. With this in mind, we investigate the following research questions in this paper: “How difficult is the ‘both teams to score’ (BTTS) prediction problem?”, “Are machine learning classifiers capable of predicting BTTS better than bookmakers?”, and “Are machine learning classifiers useful for devising profitable betting strategies in the BTTS market?”. We collected historical football data, extracted groups of features to represent the teams’ strengths, and fed these to state-of-the-art classification models. We performed a comprehensive set of experiments and showed that, although hard to predict, in some scenarios it is possible to outperform bookmakers, which are robust baselines per se. More importantly, in some cases it is possible to beat the market and devise profitable strategies based on machine learning algorithms. The results are encouraging and, besides shedding light on the problem, may provide novel insights for all kinds of football stakeholders.     

Kaggle forecasting competitions: An overlooked learning opportunity

We review the results of six forecasting competitions based on the online data science platform Kaggle, which have been largely overlooked by the forecasting community. In contrast to the M competitions, the competitions reviewed in this study feature daily and weekly time series with exogenous variables, business hierarchy information, or both. Furthermore, the Kaggle data sets all exhibit higher entropy than the M3 and M4 competitions, and they are intermittent.In this review, we confirm the conclusion of the M4 competition that ensemble models using cross-learning tend to outperform local time series models and that gradient boosted decision trees and neural networks are strong forecast methods. Moreover, we present insights regarding the use of external information and validation strategies, and discuss the impacts of data characteristics on the choice of statistics or machine learning methods. Based on these insights, we construct nine ex-ante hypotheses for the outcome of the M5 competition to allow empirical validation of our findings.