|
on Forecasting |
| By: | Sidra Mehtab; Jaydip Sen |
| Abstract: | Prediction of future movement of stock prices has been a subject matter of many research work. In this work, we propose a hybrid approach for stock price prediction using machine learning and deep learning-based methods. We select the NIFTY 50 index values of the National Stock Exchange of India, over a period of four years, from January 2015 till December 2019. Based on the NIFTY data during the said period, we build various predictive models using machine learning approaches, and then use those models to predict the Close value of NIFTY 50 for the year 2019, with a forecast horizon of one week. For predicting the NIFTY index movement patterns, we use a number of classification methods, while for forecasting the actual Close values of NIFTY index, various regression models are built. We, then, augment our predictive power of the models by building a deep learning-based regression model using Convolutional Neural Network with a walk-forward validation. The CNN model is fine-tuned for its parameters so that the validation loss stabilizes with increasing number of iterations, and the training and validation accuracies converge. We exploit the power of CNN in forecasting the future NIFTY index values using three approaches which differ in number of variables used in forecasting, number of sub-models used in the overall models and, size of the input data for training the models. Extensive results are presented on various metrics for all classification and regression models. The results clearly indicate that CNN-based multivariate forecasting model is the most effective and accurate in predicting the movement of NIFTY index values with a weekly forecast horizon. |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2001.09769&r=all |
| By: | Riza Demirer (Department of Economics and Finance, Southern Illinois University Edwardsville, Edwardsville, IL 62026-1102, USA); Rangan Gupta (Department of Economics, University of Pretoria, Pretoria, 0002, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany); Syed Jawad Hussain Shahzad (Montpellier Business School, Montpellier, France and South Ural State University, Chelyabinsk, Russian Federation) |
| Abstract: | We examine the predictive power of disentangled oil price shocks over gold market volatility via the heterogeneous autoregressive realized volatility (HAR-RV) model. Our in- and out-of-sample tests show that combining the information from both oil supply and demand shocks with the innovations associated with financial market risks improves the forecast accuracy of realized volatility of gold. While financial risk shocks are important on their own, including oil price shocks in the model provides additional forecasting power in out-of-sample tests. Compared to the benchmark HAR-RV model, the extended model with all the three shocks included outperforms, in a statistically significant manner, all other variants of the HAR-RV framework for short-, medium, and long-run forecasting horizons. The findings highlight the predictive power of cross-market information in commodities and suggest that disentangling supply and demand related factors associated with price shocks could help improve the accuracy of forecasting models. |
| Keywords: | Oil Shocks, Risk Shocks, Gold, Realized Volatility, Forecasting |
| JEL: | C22 C53 Q02 |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202010&r=all |
| By: | Matteo Bonato (Department of Economics and Econometrics, University of Johannesburg, Auckland Park, South Africa and IPAG Business School, 184 Boulevard Saint-Germain, 75006 Paris, France); Konstantinos Gkillas (Department of Business Administration, University of Patras – University Campus, Rio, P.O. Box 1391, 26500 Patras, Greece); Rangan Gupta (Department of Economics, University of Pretoria, Pretoria, 0002, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany) |
| Abstract: | We apply the heterogeneous autoregressive realized volatility (HAR-RV) model to examine the importance of investor happiness in predicting the daily realized volatility of gold returns. We estimate daily realized volatility by employing intraday data providing both in-sample and out-of sample predictions. Our in-sample results reveal that realized volatility is negatively linked to investor happiness. Moreover, our out-of-sample results show that extending the HAR-RV model to include investor happiness significantly improves the accuracy of forecasts of realized volatility at short- and medium-run forecast horizons. |
| Keywords: | Investor Happiness, Gold, Realized Volatility, Forecasting |
| JEL: | G15 G17 Q02 |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202004&r=all |
| By: | Matteo Bonato (Department of Economics and Econometrics, University of Johannesburg, Auckland Park, South Africa and IPAG Business School, 184 Boulevard Saint-Germain, 75006 Paris, France); Konstantinos Gkillas (Department of Business Administration, University of Patras – University Campus, Rio, P.O. Box 1391, 26500 Patras, Greece); Rangan Gupta (Department of Economics, University of Pretoria, Pretoria, 0002, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany) |
| Abstract: | We use the heterogeneous autoregressive realized volatility (HAR-RV) model to analyze both in sample and out-of-sample whether a measure of investor happiness predicts the daily realized volatility of oil-price returns, where we use high-frequency intradaily data to measure realized volatility. Full-sample estimates reveal that realized volatility is significantly negatively linked to investor happiness at a short forecast horizon. Similarly, out-of-sample results indicate that investor happiness significantly improves accuracy of forecasts of realized volatility at a short forecast horizon. Results for a medium and a long forecast horizon are insignificant. We argue that our results shed light on the role played by speculation in oil products and the potential function of oil-related products as a hedge against risks in traditional financial assets. |
| Keywords: | Investor Happiness, Oil market, Realized Volatility, Forecasting |
| JEL: | G15 G17 Q02 |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202009&r=all |
| By: | Tine Van Calster; Filip Van den Bossche; Bart Baesens; Wilfried Lemahieu |
| Abstract: | Choosing the technique that is the best at forecasting your data, is a problem that arises in any forecasting application. Decades of research have resulted into an enormous amount of forecasting methods that stem from statistics, econometrics and machine learning (ML), which leads to a very difficult and elaborate choice to make in any forecasting exercise. This paper aims to facilitate this process for high-level tactical sales forecasts by comparing a large array of techniques for 35 times series that consist of both industry data from the Coca-Cola Company and publicly available datasets. However, instead of solely focusing on the accuracy of the resulting forecasts, this paper introduces a novel and completely automated profit-driven approach that takes into account the expected profit that a technique can create during both the model building and evaluation process. The expected profit function that is used for this purpose, is easy to understand and adaptable to any situation by combining forecasting accuracy with business expertise. Furthermore, we examine the added value of ML techniques, the inclusion of external factors and the use of seasonal models in order to ascertain which type of model works best in tactical sales forecasting. Our findings show that simple seasonal time series models consistently outperform other methodologies and that the profit-driven approach can lead to selecting a different forecasting model. |
| Date: | 2020–02 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2002.00949&r=all |
| By: | Wheeler, Andrew Palmer (University of Texas at Dallas); Steenbeek, Wouter |
| Abstract: | Objectives: We illustrate how a machine learning algorithm, Random Forests, can provide accurate long-term predictions of crime at micro places relative to other popular techniques. We also show how recent advances in model summaries can help to open the ‘black box’ of Random Forests, considerably improving their interpretability. Methods: We generate long-term crime forecasts for robberies in Dallas at 200 by 200 feet grid cells that allow spatially varying associations of crime generators and demographic factors across the study area. We then show how using interpretable model summaries facilitate understanding the model’s inner workings. Results: We find that Random Forests greatly outperform Risk Terrain Models and Kernel Density Estimation in terms of forecasting future crimes using different measures of predictive accuracy, but only slightly outperform using prior counts of crime. We find different factors that predict crime are highly non-linear and vary over space. Conclusions: We show how using black-box machine learning models can provide accurate micro placed based crime predictions, but still be interpreted in a manner that fosters understanding of why a place is predicted to be risky. Data and code to replicate the results can be downloaded from https://www.dropbox.com/sh/b3n9a6z5xw14r d6/AAAjqnoMVKjzNQnWP9eu7M1ra?dl=0 |
| Date: | 2020–01–18 |
| URL: | http://d.repec.org/n?u=RePEc:osf:socarx:xc538&r=all |
| By: | Jaqueson K. Galimberti (School of Economics, Auckland University of Technology) |
| Abstract: | We evaluate the usefulness of satellite-based data on night-time lights for forecasting GDP growth across a global sample of countries, proposing innovative location-based indicators to extract new predictive information from the lights data. Our findings are generally favorable to the use of night lights data to improve the accuracy of model-based forecasts. We also find a substantial degree of heterogeneity across countries in the relationship between lights and economic activity: individually-estimated models tend to outperform panel specifications. Key factors underlying the night lights performance include the country’s size and income level, logistics infrastructure, and the quality of national statistics. |
| Keywords: | night lights, remote sensing, big data, business cycles, leading indicators |
| JEL: | C55 C82 E01 E37 R12 |
| Date: | 2019–12 |
| URL: | http://d.repec.org/n?u=RePEc:aut:wpaper:202002&r=all |
| By: | Muhammad Ejaz (State Bank of Pakistan); Javed Iqbal (State Bank of Pakistan) |
| Abstract: | It is essential for policy makers to timely consider the cyclical changes in output. Monthly industrial production is one of the most important and commonly used macroeconomic indicators for this purpose. In Pakistan monthly estimates of industrial production are not available. Alternatively, policy makers rely on Large Scale Manufacturing (LSM) index which accounts for only 10% of the GDP. Another limitation of LSM is that it mainly accounts for private sector industry thus leaving out direct public sector presence in industrial production. LSM is relied upon heavily by economic policy makers to gauge economic activity in Pakistan. In this paper, we present a new Industrial Production Index (IPI), which covers whole of industrial sector in Pakistan. The advantage of this IPI index is that it provides additional information that LSM misses out. Post estimation, we built seven econometrics models reflecting conditions in real, financial and external sectors to estimate YoY changes in the proposed Instrial Production Index (IPI). Our results show that the root mean square error of the ARDL model reflecting financial conditions is lowest across all horizons |
| Keywords: | Economic Indicator, Industry Studies, Econometric Forecasting |
| JEL: | L60 C80 C53 |
| Date: | 2019–04 |
| URL: | http://d.repec.org/n?u=RePEc:sbp:wpaper:103&r=all |
| By: | Zhengkun Li; Minh-Ngoc Tran; Chao Wang; Richard Gerlach; Junbin Gao |
| Abstract: | Value-at-Risk (VaR) and Expected Shortfall (ES) are widely used in the financial sector to measure the market risk and manage the extreme market movement. The recent link between the quantile score function and the Asymmetric Laplace density has led to a flexible likelihood-based framework for joint modelling of VaR and ES. It is of high interest in financial applications to be able to capture the underlying joint dynamics of these two quantities. We address this problem by developing a hybrid model that is based on the Asymmetric Laplace quasi-likelihood and employs the Long Short-Term Memory (LSTM) time series modelling technique from Machine Learning to capture efficiently the underlying dynamics of VaR and ES. We refer to this model as LSTM-AL. We adopt the adaptive Markov chain Monte Carlo (MCMC) algorithm for Bayesian inference in the LSTM-AL model. Empirical results show that the proposed LSTM-AL model can improve the VaR and ES forecasting accuracy over a range of well-established competing models. |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:arx:papers:2001.08374&r=all |
| By: | Elie Bouri (USEK Business School, Holy Spirit University of Kaslik, Jounieh, Lebanon); Konstantinos Gkillas (Department of Business Administration, University of Patras – University Campus, Rio, P.O. Box 1391, 26500 Patras, Greece); Rangan Gupta (Department of Economics, University of Pretoria, Pretoria, 0002, South Africa); Christian Pierdzioch (Department of Economics, Helmut Schmidt University, Holstenhofweg 85, P.O.B. 700822, 22008 Hamburg, Germany) |
| Abstract: | We analyze the role of the US-China trade war in predicting, both in- and out-of-sample, daily realized volatility of Bitcoin returns. We study intraday data spanning from 1st July 2017 to 30th June 2019. We use the heterogeneous autoregressive realized volatility model (HAR-RV) as the benchmark model to capture stylized facts such as heterogeneity and long-memory. We then extend the HAR-RV model to include a metric of US-China trade tensions. This is our primary predictor of interest, and it is based on Google Trends. We also control for jumps, realized skewness, and realized kurtosis. For our empirical analysis, we use a machine-learning technique which is known as random forests. Our findings reveal that US-China trade uncertainty does improve forecast accuracy for various configurations of random forests and forecast horizons. |
| Keywords: | Bitcoin, Realized volatility, Trade war, Random forests |
| JEL: | G17 Q02 Q47 |
| Date: | 2020–01 |
| URL: | http://d.repec.org/n?u=RePEc:pre:wpaper:202003&r=all |
| By: | Turchin, Peter; Korotayev, Andrey |
| Abstract: | This article revisits the prediction, made in 2010, that the 2010–2020 decade would likely be a period of growing instability in the United States and Western Europe (Turchin 2010). This prediction was based on a computational model that quantified in the USA such structural-demographic forces for instability as popular immiseration, intraelite competition, and state weakness prior to 2010. Using these trends as inputs, the model calculated and projected forward in time the Political Stress Index, which in the past was strongly correlated with socio-political instability. Ortmans et al. (2017) conducted a similar structural-demographic study for the United Kingdom and obtained similar results. Here we use the Cross-National Time-Series Data Archive for the US, UK, and Western European countries to assess these structural-demographic predictions. We find that such measures of socio-political instability as anti-government demonstrations and riots increased dramatically during the 2010–2020 decade in all of these countries. |
| Date: | 2020–01–12 |
| URL: | http://d.repec.org/n?u=RePEc:osf:socarx:7ahqn&r=all |