The power of text-based indicators in forecasting Italian economic activity

Can we use newspaper articles to forecast economic activity? Our answer is yes; and, to this end, we propose a high-frequency Text-based Economic Sentiment Index (TESI) and a Text-based Economic Policy Uncertainty (TEPU) for Italy. Novel survey evidence regarding Italian firms and households supports the rationale behind studying text data for the purposes of forecasting. Such indices are extracted from approximately 1.5 million articles from 4 popular newspapers, using a novel Italian economic dictionary with valence shifters. The TESI and TEPU can be updated daily for the whole economy and for specific sectors or economic topics. To test the predictive power of our indicators, we propose two forecasting exercises. Firstly, we use Bayesian Model Averaging (BMA) techniques to show that our monthly text-based indicators greatly reduce the uncertainty surrounding the short-term predictions of the main macroeconomic aggregates, especially during recessions. Secondly, we employ these indices in a weekly GDP tracker, achieving sizeable gains in forecasting accuracy, both in normal and turbulent times.     

The era of Omni-learning: Frameworks and practices of the expanded human resource development

According to the ever-changing organizational environment, we also adopt an ever-expanding HRD in contents and scope. Focusing on the drivers of the recent HRD reforms, the growing demand for organizational agility and holistic capabilities of human resources is driving the need for change, and the pandemic crisis is pushing the revolutionary changes of HRD. Such trends of the expanded HRD can be characterized as a ‘march toward Omni-learning’. In specific, there are at least four noticeable and intertwined waves of HRD reforms toward Omni-learning: (1) embracing holistic capabilities such as benchmarking, modeling, forecasting, and backcasting (BMFB); (2) integrating working and learning by promoting on-the-job learning (OJL), on-the-life learning (OLL), and on-the-life training (OLT); (3) standardizing communication tools such as LMF (logic tree; multi-dimensional matrix/map; flowchart) and EEOSP (everything/everyone on the same page); and (4) diversifying communication space-time across diverse places (close; remote) and times (synchronized; a-synchronized). And all the HRD waves are commonly facilitated and promoted by technological breakthroughs of artificial intelligence (AI) and the metaverse. Beyond the current innovations of HRD, no one would be certain about the answer to the question “What’s next?”. But what is certain is that HRD will continue to be deepened and widened as long as human resources are needed to respond to the ever-changing organizational environment.     

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.     

Forecasts for international financial series with VMD algorithms

Recent models with variational mode decomposition (VMD) have been applied to time-series forecasting. In this paper, we build a hybrid model named VMD–autoregressive integrated moving average (ARIMA)–Taylor expansion forecasting (TEF) to increase accuracy and stability for predicting financial time series. We use VMD algorithms to decompose financial series into subseries. An ARIMA model is built to predict each mode’s linear component, and the pragmatic TEF model based on a tracking differentiator is applied to forecast of the nonlinear component. Then the forecasts of all subseries are assembled as a final forecast. Our empirical results of international stock indices demonstrate that the proposed hybrid approach surpasses several existing state-of-the-art hybrid models.     

Parameter-efficient deep probabilistic forecasting

Probabilistic time series forecasting is crucial in many application domains, such as retail, ecommerce, finance, and biology. With the increasing availability of large volumes of data, a number of neural architectures have been proposed for this problem. In particular, Transformer-based methods achieve state-of-the-art performance on real-world benchmarks. However, these methods require a large number of parameters to be learned, which imposes high memory requirements on the computational resources for training such models. To address this problem, we introduce a novel bidirectional temporal convolutional network that requires an order of magnitude fewer parameters than a common Transformer-based approach. Our model combines two temporal convolutional networks: the first network encodes future covariates of the time series, whereas the second network encodes past observations and covariates. We jointly estimate the parameters of an output distribution via these two networks. Experiments on four real-world datasets show that our method performs on par with four state-of-the-art probabilistic forecasting methods, including a Transformer-based approach and WaveNet, on two point metrics (sMAPE and NRMSE) as well as on a set of range metrics (quantile loss percentiles) in the majority of cases. We also demonstrate that our method requires significantly fewer parameters than Transformer-based methods, which means that the model can be trained faster with significantly lower memory requirements, which as a consequence reduces the infrastructure cost for deploying these models.     

False dichotomy alert: Improving subjective-probability estimates vs. raising awareness of systemic risk

Taleb et al. (2022) portray the superforecasting research program as a masquerade that purports to build “survival functions for tail assessments via sports-like tournaments.” But that never was the goal. The program was designed to help intelligence analysts make better probability judgments, which required posing rapidly resolvable questions. From a signal detection theory perspective, the superforecasting and Taleb et al. programs are complementary, not contradictory (a point Taleb and Tetlock (2013) recognized). The superforecasting program aims at achieving high hit rates at low cost in false-positives, whereas Taleb et al. prioritize alerting us to systemic risk, even if that entails a high false-positive rate. Proponents of each program should, however, acknowledge weaknesses in their cases. It is unclear: (a) how Taleb et al. (2022) can justify extreme error-avoidance trade-offs, without tacit probability judgments of rare, high-impact events; (b) how much superforecasting interventions can improve probability judgments of such events.     

The RWDAR model: A novel state-space approach to forecasting

This paper introduces the Random Walk with Drift plus AutoRegressive model (RWDAR) for time-series forecasting. Owing to the presence of a random walk plus drift term, this model shares some similarities with the Theta model of Assimakopoulos and Nikolopoulos (2000). However, the addition of a first-order autoregressive term in the state equation provides additional adaptability and flexibility. Indeed, it is shown that RWDAR tends to outperform the Theta model when forecasting both stationary and nearly non-stationary time series. This paper also proposes a simple estimation method for the RWDAR model based on the solution of the algebraic Riccati equation for the prediction error covariance of the state vector. Simulation results show that this estimator performs as well as the standard Kalman filter approach. Finally, using yearly data from the M3 and M4 competition datasets, it is found that RWDAR outperforms traditional forecasting methods.