nep-for New Economics Papers
on Forecasting
Issue of 2021‒04‒12
eleven papers chosen by
Rob J Hyndman
Monash University

  1. CRPS Learning By Jonathan Berrisch; Florian Ziel
  2. A new approach to exchange rate forecast: The role of global financial cycle and time-varying parameters By Raheem, Ibrahim; Vo, Xuan Vinh
  3. Models, Markets, and the Forecasting of Elections By Rajiv Sethi; Julie Seager; Emily Cai; Daniel M. Benjamin; Fred Morstatter
  4. Forecasting with Deep Learning: S&P 500 index By Firuz Kamalov; Linda Smail; Ikhlaas Gurrib
  5. Short-Term Covid-19 Forecast for Latecomers By Marcelo Medeiros; Alexandre Street; Davi Vallad\~ao; Gabriel Vasconcelos; Eduardo Zilberman
  6. A reality check on the GARCH-MIDAS volatility models By Virk, Nader; Javed, Farrukh; Awartani, Basel
  7. Predicting Inflation with Neural Networks By Livia Paranhos
  8. Global financial cycles and exchange rate forecast: A factor analysis By Raheem, Ibrahim
  9. The Properly Use of Google Trends in Forecasting Models By Marcelo C. Medeiros; Henrique F. Pires
  10. Accurate Stock Price Forecasting Using Robust and Optimized Deep Learning Models By Jaydip Sen; Sidra Mehtab
  11. A Stochastic Time Series Model for Predicting Financial Trends using NLP By Pratyush Muthukumar; Jie Zhong

  1. By: Jonathan Berrisch; Florian Ziel
    Abstract: Combination and aggregation techniques can improve forecast accuracy substantially. This also holds for probabilistic forecasting methods where full predictive distributions are combined. There are several time-varying and adaptive weighting schemes like Bayesian model averaging (BMA). However, the performance of different forecasters may vary not only over time but also in parts of the distribution. So one may be more accurate in the center of the distributions, and other ones perform better in predicting the distribution's tails. Consequently, we introduce a new weighting procedure that considers both varying performance across time and the distribution. We discuss pointwise online aggregation algorithms that optimize with respect to the continuous ranked probability score (CRPS). After analyzing the theoretical properties of a fully adaptive Bernstein online aggregation (BOA) method, we introduce smoothing procedures for pointwise CRPS learning. The properties are confirmed and discussed using simulation studies. Additionally, we illustrate the performance in a forecasting study for carbon markets. In detail, we predict the distribution of European emission allowance prices.
    Date: 2021–02
  2. By: Raheem, Ibrahim; Vo, Xuan Vinh
    Abstract: The exchange rate disconnect puzzle argues that macroeconomic fundamentals are not able to accurately predict exchange rate. Recent studies have shown that the puzzle could be upturned if: (a) the dataset is structured in a panel form; (b) the model is based on the portfolio balance theory (PBT); (c) factor models are employed and (d) time-varying parameter (TVP) regression is used. This study combines these strands of the literature. Essentially, the study conjectures that Global Financial Cycle (GFCy), drawing inspiration from PBT, has some predictive information content on exchange rate. Using dataset from 25 countries, we produced some mixed results. On the whole, the GFCy is able to produce lower forecast error, as compared to the that of benchmark model. However, its effectiveness is dependent upon the regression type (TVP vs. Panel Fixed Effect); forecast horizons (short vs. long); the sample period (early vs. late) and measures of GFCy. The results are robust to a number of checks.
    Keywords: exchange rate, forecasting, global financial cycle and time-varying parameters
    JEL: F31
    Date: 2020
  3. By: Rajiv Sethi; Julie Seager; Emily Cai; Daniel M. Benjamin; Fred Morstatter
    Abstract: We examine probabilistic forecasts for battleground states in the 2020 US presidential election, using daily data from two sources over seven months: a model published by The Economist, and prices from the PredictIt exchange. We find systematic differences in accuracy over time, with markets performing better several months before the election, and the model performing better as the election approached. A simple average of the two forecasts performs better than either one of them overall, even though no average can outperform both component forecasts for any given state-date pair. This effect arises because the model and the market make different kinds of errors in different states: the model was confidently wrong in some cases, while the market was excessively uncertain in others. We conclude that there is value in using hybrid forecasting methods, and propose a market design that incorporates model forecasts via a trading bot to generate synthetic predictions. We also propose and conduct a profitability test that can be used as a novel criterion for the evaluation of forecasting performance.
    Date: 2021–02
  4. By: Firuz Kamalov; Linda Smail; Ikhlaas Gurrib
    Abstract: Stock price prediction has been the focus of a large amount of research but an acceptable solution has so far escaped academics. Recent advances in deep learning have motivated researchers to apply neural networks to stock prediction. In this paper, we propose a convolution-based neural network model for predicting the future value of the S&P 500 index. The proposed model is capable of predicting the next-day direction of the index based on the previous values of the index. Experiments show that our model outperforms a number of benchmarks achieving an accuracy rate of over 55%.
    Date: 2021–03
  5. By: Marcelo Medeiros; Alexandre Street; Davi Vallad\~ao; Gabriel Vasconcelos; Eduardo Zilberman
    Abstract: The number of Covid-19 cases is increasing dramatically worldwide. Therefore, the availability of reliable forecasts for the number of cases in the coming days is of fundamental importance. We propose a simple statistical method for short-term real-time forecasting of the number of Covid-19 cases and fatalities in countries that are latecomers -- i.e., countries where cases of the disease started to appear some time after others. In particular, we propose a penalized (LASSO) regression with an error correction mechanism to construct a model of a latecomer in terms of the other countries that were at a similar stage of the pandemic some days before. By tracking the number of cases and deaths in those countries, we forecast through an adaptive rolling-window scheme the number of cases and deaths in the latecomer. We apply this methodology to Brazil, and show that (so far) it has been performing very well. These forecasts aim to foster a better short-run management of the health system capacity.
    Date: 2020–04
  6. By: Virk, Nader (Plymouth Business School); Javed, Farrukh (Örebro University School of Business); Awartani, Basel (Westminster Business School)
    Abstract: We employ a battery of model evaluation tests for a broad-set of GARCH-MIDAS models and account for data snooping bias. We document that inferences based on standard tests for GM variance components can be misleading. Our data mining free results show that the gains of macro-variables in forecasting total (long run) variance by GM models are overstated (understated). Estimation of different components of volatility is crucial for designing differentiated investing strategies, risk management plans and pricing of derivative securities. Therefore, researchers and practitioners should be wary of data mining bias, which may contaminate a forecast that may appear statistically validated using robust evaluation tests.
    Keywords: GARCH-MIDAS models; component variance forecasts; macro-variables; data snooping
    JEL: C32 C52 G11 G17
    Date: 2021–03–30
  7. By: Livia Paranhos
    Abstract: This paper applies neural network models to forecast inflation. The use of a particular recurrent neural network, the long-short term memory model, or LSTM, that summarizes macroeconomic information into common components is a major contribution of the paper. Results from an exercise with US data indicate that the estimated neural nets usually present better forecasting performance than standard benchmarks, especially at long horizons. The LSTM in particular is found to outperform the traditional feed-forward network at long horizons, suggesting an advantage of the recurrent model in capturing the long-term trend of inflation. This finding can be rationalized by the so called long memory of the LSTM that incorporates relatively old information in the forecast as long as accuracy is improved, while economizing in the number of estimated parameters. Interestingly, the neural nets containing macroeconomic information capture well the features of inflation during and after the Great Recession, possibly indicating a role for nonlinearities and macro information in this episode. The estimated common components used in the forecast seem able to capture the business cycle dynamics, as well as information on prices.
    Date: 2021–04
  8. By: Raheem, Ibrahim
    Abstract: This study applies portfolio balance theory in forecasting exchange rate. The study further argues for the need to account for the role of Global Financial Cycle (GFCy). As such, the first stage of the analysis is estimate a GFCy model and obtain the idiosyncratic shock. Next, we use the results in the first stage as a predictor for exchange rate. The study builds dataset for 20 advanced and emerging countries from 1990Q1- 2017Q2. Among other things, there are three important results to note. First, our approach to forecast exchange rate is able to beat the benchmark random walk model. Second, the best prediction is made at short term forecasting horizons, i.e. 1 and 4 quarters forecast ahead. Third, the performance of the early sample size outweighs that of the late sample size.
    Keywords: Exchange rate; Factor models; Global financial cycle; Forecasting
    JEL: E3 E37 F31
    Date: 2020
  9. By: Marcelo C. Medeiros; Henrique F. Pires
    Abstract: It is widely known that \texttt{Google Trends} has become one of the most popular free tools used by forecasters both in academics and in the private and public sectors. There are many papers, from several different fields, concluding that \texttt{Google Trends} improve forecasts' accuracy. However, what seems to be widely unknown, is that each sample of Google search data is different from the other, even if you set the same search term, data and location. This means that it is possible to find arbitrary conclusions merely by chance. This paper aims to show why and when it can become a problem and how to overcome this obstacle.
    Date: 2021–04
  10. By: Jaydip Sen; Sidra Mehtab
    Abstract: Designing robust frameworks for precise prediction of future prices of stocks has always been considered a very challenging research problem. The advocates of the classical efficient market hypothesis affirm that it is impossible to accurately predict the future prices in an efficiently operating market due to the stochastic nature of the stock price variables. However, numerous propositions exist in the literature with varying degrees of sophistication and complexity that illustrate how algorithms and models can be designed for making efficient, accurate, and robust predictions of stock prices. We present a gamut of ten deep learning models of regression for precise and robust prediction of the future prices of the stock of a critical company in the auto sector of India. Using a very granular stock price collected at 5 minutes intervals, we train the models based on the records from 31st Dec, 2012 to 27th Dec, 2013. The testing of the models is done using records from 30th Dec, 2013 to 9th Jan 2015. We explain the design principles of the models and analyze the results of their performance based on accuracy in forecasting and speed of execution.
    Date: 2021–03
  11. By: Pratyush Muthukumar; Jie Zhong
    Abstract: Stock price forecasting is a highly complex and vitally important field of research. Recent advancements in deep neural network technology allow researchers to develop highly accurate models to predict financial trends. We propose a novel deep learning model called ST-GAN, or Stochastic Time-series Generative Adversarial Network, that analyzes both financial news texts and financial numerical data to predict stock trends. We utilize cutting-edge technology like the Generative Adversarial Network (GAN) to learn the correlations among textual and numerical data over time. We develop a new method of training a time-series GAN directly using the learned representations of Naive Bayes' sentiment analysis on financial text data alongside technical indicators from numerical data. Our experimental results show significant improvement over various existing models and prior research on deep neural networks for stock price forecasting.
    Date: 2021–02

This nep-for issue is ©2021 by Rob J Hyndman. It is provided as is without any express or implied warranty. It may be freely redistributed in whole or in part for any purpose. If distributed in part, please include this notice.
General information on the NEP project can be found at For comments please write to the director of NEP, Marco Novarese at <>. Put “NEP” in the subject, otherwise your mail may be rejected.
NEP’s infrastructure is sponsored by the School of Economics and Finance of Massey University in New Zealand.