Search site...

Nowcasting at Autonomy

Jeremy Kwok

14th October 2024

Introduction

Nowcasting, a term derived from “now” and “forecasting,” refers to the prediction of the present, the very near future, and the very recent past. It is particularly significant in economics and social policy, where timely and accurate data are crucial for decision-making by policymakers, businesses, and other actors.

The necessity for nowcasting arises from the time lags associated with the publication of official economic statistics (e.g. ONS data sets). As examples, Gross Domestic Product (GDP) figures are typically released with a delay of several months and deprivation-relevant data is often only published on an annual or even less regular basis. During these time lags, economic and social conditions can change, and decision-makers need current data to navigate the present economic landscape effectively.

At the Autonomy Institute, we will be spending the next three years developing and fine-tuning nowcasting methods in order to provide better, more up to date information for policymakers and researchers.

The value of nowcasting

The importance of nowcasting lies in its ability to bridge the informational gap caused by delays in the publication of official economic statistics. Nowcasting addresses this issue by providing up-to-date estimates that reflect the current state of the economy and society, thereby enhancing the responsiveness and effectiveness of policies and strategies (Banbura, Giannone, & Reichlin, 2010). For example, during the Covid pandemic, nowcasting models were instrumental in providing timely assessments of economic activity, which were crucial for the swift implementation of fiscal and monetary policies (Lenza & Primiceri, 2020).

The ability to use real-time data from various sources, including financial markets, social media, patient registries and other high-frequency indicators, allows nowcasting models to capture sudden socio-economic shifts more effectively than traditional forecasting methods.

The ability to use real-time data from various sources, including financial markets, social media, patient registries and other high-frequency indicators, allows nowcasting models to capture sudden socio-economic shifts more effectively than traditional forecasting methods.

Nowcasting is distinct from traditional forecasting due to its reliance on contemporaneous data and the unique challenges this entails. Unlike forecasting, which predicts future values, nowcasting aims to estimate the present state of economic variables, such as GDP, using current high-frequency data like retail sales, traffic, and energy consumption. One major difference lies in the data timing and availability. Forecasts are generally based on past data to predict future trends, whereas nowcasting integrates real-time data, which may still be incomplete or subject to revisions. This introduces significant complexity in ensuring the robustness of the nowcast models against structural breaks and measurement errors, which are more prevalent in real-time data scenarios.

What can/should we nowcast?

There is a growing tendency to use real-time indicators as predictors for nowcasting, which refers to data recorded as soon as an event occurs. Real-time data includes daily financial data (Andreou et al., 2013), financial transactions from automated teller machines and point-of-sale machines (Dias et al., 2015; Duarte et al., 2017), mobility data (Askitas & Zimmermann, 2013), newspaper content data (Aguilar et al., 2021; Ardia et al., 2021), and Google trends (Bulut, 2018; Iselin & Siliverstovs, 2016). At Autonomy, we can use data from our Annual Deprivation Index (crime data, health deprivation data and claimant counts) to nowcast the deprivation picture of England for example.

Today’s data-saturated world allows for more rigorous and sophisticated interpretations, so the key task for researchers is navigating the plethora of indicators and making sense of the data. My task over the coming months and years is to deploy a number of models, using data from different socio-economic domains to provide unique data sets that are useful for policymakers and researchers. We welcome any collaborations as we pursue this ambitious agenda – please get in touch if this is relevant to your work.

Indicative bibliography
  • Andreou, E., Ghysels, E. and Kourtellos, A., 2013. Should macroeconomic forecasters use daily financial data and how?. Journal of Business & Economic Statistics, 31(2), pp.240-251.
  • Aguilar, P., Ghirelli, C., Pacce, M. and Urtasun, A., 2021. Can news help measure economic sentiment? An application in COVID-19 times. Economics Letters, 199, p.109730.
  • Antipa, P., Barhoumi, K., Brunhes-Lesage, V. and Darné, O., 2012. Nowcasting German GDP: A comparison of bridge and factor models. Journal of Policy Modeling, 34(6), pp.864-878.
  • Ardia, D., Bluteau, K. and Kassem, A., 2021. A century of Economic Policy Uncertainty through the French–Canadian lens. Economics Letters, 205, p.109938.
  • Artola, C., Pinto, F. and de Pedraza García, P., 2015. Can internet searches forecast tourism inflows?. International Journal of Manpower, 36(1), pp.103-116.
  • Askitas, N. and Zimmermann, K.F., 2009. Google econometrics and unemployment forecasting. Applied Economics Quarterly, (2), pp.107-120.
  • Bangwayo-Skeete, P.F. and Skeete, R.W., 2015. Can Google data improve the forecasting performance of tourist arrivals? Mixed-data sampling approach. Tourism Management, 46, pp.454-464.
  • Bańbura, M., Giannone, D., Modugno, M. and Reichlin, L., 2013. Now-casting and the real-time data flow. In Handbook of economic forecasting (Vol. 2, pp. 195-237). Elsevier.
  • Blasques, F., Koopman, S. J., Mallee, M., & Zhang, Z. (2016). Weighted maximum likelihood for dynamic factor analysis and forecasting with mixed frequency data. Journal of Econometrics, 193(2), 405–417
  • Blazquez, D. and Domenech, J., 2018. Big Data sources and methods for social and economic analyses. Technological Forecasting and Social Change, 130, pp.99-113.
  • Bollen, J., Mao, H. and Zeng, X., 2011. Twitter mood predicts the stock market. Journal of computational science, 2(1), pp.1-8.
  • Bragoli, D., & Modugno, M. (2017). A now-casting model for Canada: Do U.S. variables matter? International Journal of Forecasting, 33(4), 786–800.
  • Breitung, J. and Hafner, C.M., 2016. A simple model for now-casting volatility series. International Journal of Forecasting, 32(4), pp.1247-1255.
  • Breiman, L., 2001. Random forests. Machine learning, 45, pp.5-32.
  • Buccheri, G., Bormetti, G., Corsi, F. and Lillo, F., 2021. A score-driven conditional correlation model for noisy and asynchronous data: An application to high-frequency covariance dynamics. Journal of Business & Economic Statistics, 39(4), pp.920-936.
  • Bulligan, G., Marcellino, M. and Venditti, F., 2015. Forecasting economic activity with targeted predictors. International Journal of Forecasting, 31(1), pp.188-206.
  • Bulut, L., 2018. Google Trends and the forecasting performance of exchange rate models. Journal of Forecasting, 37(3), pp.303-315.
  • Buncic, D. and Müller, O., 2017. Measuring the output gap in Switzerland with linear opinion pools. Economic Modelling, 64, pp.153-171.
  • Burns, A. F. and Mitchell, W. C. (1946) Measuring Business Cycles. New York: National Bureau of Economic Research.
  • Burnap, P., Gibson, R., Sloan, L., Southern, R. and Williams, M., 2016. 140 characters to victory?: Using Twitter to predict the UK 2015 General Election. Electoral Studies, 41, pp.230-233.
  • Carriero, A., Clark, T.E. and Marcellino, M., 2015. Bayesian VARs: specification choices and forecast accuracy. Journal of Applied Econometrics, 30(1), pp.46-73.
  • Carnot, N., Koen, V. and Tissot, B., 2011. Economic forecasting and policy. Springer.
  • Castle, J. L., Fawcett, N. W. P., & Hendry, D. F. (2009). Nowcasting is not just contemporaneous forecasting. National Institute Economic Review, 210, 71-89.
  • Cascaldi-Garcia, D., Ferreira, T.R., Giannone, D. and Modugno, M., 2024. Back to the Present: Learning about the Euro Area through a Now-casting Model. International Journal of Forecasting, 40(2), pp.661-686.
  • Cavallo, A. and Rigobon, R., 2016. The billion prices project: Using online prices for measurement and research. Journal of Economic Perspectives, 30(2), pp.151-178.
  • Cervena, M. and Schneider, M., 2014. Short-term forecasting of GDP with a DSGE model augmented by monthly indicators. International Journal of Forecasting, 30(3), pp.498-516.
  • Ceron, A., Curini, L., Iacus, S.M. and Porro, G., 2014. Every tweet counts? How sentiment analysis of social media can improve our knowledge of citizens’ political preferences with an application to Italy and France. New media & society, 16(2), pp.340-358.
  • Ceron, A. and Negri, F., 2016. The “social side” of public policy: Monitoring online public opinion and its mobilization during the policy cycle. Policy & Internet, 8(2), pp.131-147.
  • Chernis, T., & Sekkel, R. (2017). A dynamic factor model for nowcasting Canadian GDP growth. Empirical Economics, 53(1), 217–234.
  • Choi, H. and Varian, H., 2012. Predicting the present with Google Trends. Economic record, 88, pp.2-9.
  • Cuevas, A., Pérez-Quirós, G. and Quilis, E.M., 2017. Integrated model of short-term forecasting of the Spanish economy (MIPred model). Revista de Economía Aplicada, 25(74), pp.5-25.
  • Dias, F., Pinheiro, M. and Rua, A., 2015. Forecasting Portuguese GDP with factor models: Pre-and post-crisis evidence. Economic Modelling, 44, pp.266-272.
  • Del Negro, M. and Schorfheide, F., 2013. DSGE model-based forecasting. In Handbook of economic forecasting (Vol. 2, pp. 57-140). Elsevier.
  • Diebold, F.X., 1998. The past, present, and future of macroeconomic forecasting. Journal of Economic Perspectives, 12(2), pp.175-192.
  • de Carvalho, M. and Rua, A., 2017. Real-time nowcasting the US output gap: Singular spectrum analysis at work. International Journal of Forecasting, 33(1), pp.185-198.
  • Degiannakis, S., 2022. Stock market as a nowcasting indicator for real investment. Journal of Forecasting, 41(5), pp.911-919.
  • Duarte, C., Rodrigues, P.M. and Rua, A., 2017. A mixed frequency approach to the forecasting of private consumption with ATM/POS data. International Journal of Forecasting, 33(1), pp.61-75.
  • Foroni, C., Marcellino, M. and Schumacher, C., 2015. Unrestricted mixed data sampling (MIDAS): MIDAS regressions with unrestricted lag polynomials. Journal of the Royal Statistical Society Series A: Statistics in Society, 178(1), pp.57-82.
  • Fosten, J. and Gutknecht, D., 2020. Testing nowcast monotonicity with estimated factors. Journal of Business & Economic Statistics, 38(1), pp.107-123.
  • Fritsche, U. and Stephan, S. 2002 ‘Leading Indicators of German Business Cycles: An Assessment of Properties’, Journal of Economics and Statistics (Jahrbücher für Nationalökonomie und Statistik), 222(3), pp. 289-315.
  • Fuleky, P. ed., 2019. Macroeconomic forecasting in the era of big data: Theory and practice (Vol. 52). Springer Nature.
  • Garratt, A., Mitchell, J. and Vahey, S.P., 2014. Measuring output gap nowcast uncertainty. International Journal of Forecasting, 30(2), pp.268-279.
  • Ghysels, E., Santa-Clara, P. and Valkanov, R., 2004. The MIDAS touch: Mixed data sampling regression models.
  • Giannone, D., Reichlin, L. and Small, D., 2008. Nowcasting: The real-time informational content of macroeconomic data. Journal of monetary economics, 55(4), pp.665-676.
  • Gomez-Zamudio, L. M., & Ibarra, R. (2017). Are daily financial data useful for forecasting GDP? Evidence from Mexico. Economia-Journal of the Latin American and Caribbean Economic Association, 17(2), 173–203.
  • Hastie, T., Tibshirani, R., Friedman, J.H. and Friedman, J.H., 2009. The elements of statistical learning: data mining, inference, and prediction (Vol. 2, pp. 1-758). New York: springer.
  • Hochreiter, S. and Schmidhuber, J., 1997. Long short-term memory. Neural computation, 9(8), pp.1735-1780.
  • Hearst, M.A., Dumais, S.T., Osuna, E., Platt, J. and Scholkopf, B., 1998. Support vector machines. IEEE Intelligent Systems and their applications, 13(4), pp.18-28.
  • International Monetary Fund. (2022). Nowcasting GDP – A Scalable Approach Using DFM, Machine Learning and Novel Data, Applied to European Economies. Retrieved from IMF https://www.elibrary.imf.org/view/journals/001/2022/052/article-A001-en.xml.
  • Iselin, D. and Siliverstovs, B., 2016. Using newspapers for tracking the business cycle: A comparative study for Germany and Switzerland. Applied Economics, 48(12), pp.1103-1118.
  • Jansen, W.J., Jin, X. and de Winter, J.M., 2016. Forecasting and nowcasting real GDP: Comparing statistical models and subjective forecasts. International Journal of Forecasting, 32(2), pp.411-436.
  • Jokubaitis, S., Celov, D. and Leipus, R., 2021. Sparse structures with LASSO through principal components: Forecasting GDP components in the short-run. International Journal of Forecasting, 37(2), pp.759-776.
  • Kaufmann, D. and Scheufele, R., 2017. Business tendency surveys and macroeconomic fluctuations. International Journal of Forecasting, 33(4), pp.878-893.
  • Koop, G., & Korobilis, D. 2010. “Bayesian Multivariate Time Series Methods for Empirical Macroeconomics.” Foundations and Trends in Econometrics, 3(4), 267-358.
  • Litterman, R. B. (1986). “Forecasting with Bayesian Vector Autoregressions—Five Years of Experience.” Journal of Business & Economic Statistics, 4(1), 25-38.
  • Lütkepohl, H., 2013. Vector autoregressive models. In Handbook of research methods and applications in empirical macroeconomics (pp. 139-164). Edward Elgar Publishing.Marcellino, M., Porqueddu, M. and Venditti, F., 2016. Short-term GDP forecasting with a mixed-frequency dynamic factor model with stochastic volatility. Journal of Business & Economic Statistics, 34(1), pp.118-127.
  • Madhavi, K.L., Cordova, J., Ulak, M.B., Ohlsen, M., Ozguven, E.E., Arghandeh, R. and Kocatepe, A., 2017, September. Advanced electricity load forecasting combining electricity and transportation network. In 2017 North American power symposium (NAPS) (pp. 1-6). IEEE.
  • Marcellino, M. 2006 ‘Leading Indicators: What Have We Learned?’, in Elliott, G., Granger, C. W. J. and Timmermann, A. (eds) Handbook of Economic Forecasting. Amsterdam: Elsevier, pp. 879-960.
  • Nagao, S., Takeda, F. and Tanaka, R., 2019. Nowcasting of the US unemployment rate using Google Trends. Finance Research Letters, 30, pp.103-109.
  • Richardson, P., 2018. Nowcasting and the Use of Big Data in Short Term Macroeconomic Forecasting: A Critical Review. Economie et Statistique, 505(1), pp.65-87.
  • Richardson, A., van Florenstein Mulder, T. and Vehbi, T., 2021. Nowcasting GDP using machine-learning algorithms: A real-time assessment. International Journal of Forecasting, 37(2), pp.941-948.
  • Ojo, M.O., Aguiar‐Conraria, L. and Soares, M.J., 2023. The performance of OECD’s composite leading indicator. International Journal of Finance & Economics.
  • Pappalardo, L., Vanhoof, M., Gabrielli, L., Smoreda, Z., Pedreschi, D. and Giannotti, F., 2016. An analytical framework to nowcast well-being using mobile phone data. International Journal of Data Science and Analytics, 2, pp.75-92.
  • Polson, N.G. and Sokolov, V.O., 2017. Deep learning for short-term traffic flow prediction. Transportation Research Part C: Emerging Technologies, 79, pp.1-17.
  • Proietti, T., Giovannelli, A., Ricchi, O., Citton, A., Tegami, C. and Tinti, C., 2021. Nowcasting GDP and its components in a data-rich environment: The merits of the indirect approach. International Journal of Forecasting, 37(4), pp.1376-1398.
  • Preis, T., Moat, H.S. and Stanley, H.E., 2013. Quantifying trading behavior in financial markets using Google Trends. Scientific reports, 3(1), pp.1-6.
  • Preis, T. and Moat, H.S., 2014. Adaptive nowcasting of influenza outbreaks using Google searches. Royal Society open science, 1(2), p.140095.
  • Silver, M. and Heravi, S., 2001. Scanner data and the measurement of inflation. The Economic Journal, 111(472), pp.383-404.
  • S&P Global. (2020). Nowcasting European GDP during an economic shock. Retrieved from S&P Global https://www.spglobal.com/marketintelligence/en/mi/research-analysis/measuring-the-economy-jan24.html .
  • Stundziene, A., Pilinkiene, V., Bruneckiene, J., Grybauskas, A., Lukauskas, M. and Pekarskiene, I., 2023. Future directions in nowcasting economic activity: A systematic literature review. Journal of Economic Surveys.
  • Stock, J. H. and Watson, M. W. (1989) ‘New Indexes of Coincident and Leading Economic Indicators’, NBER Macroeconomics Annual, 4, pp. 351-393.
  • Qi, Y., 2012. Random forest for bioinformatics. Ensemble machine learning: Methods and applications, pp.307-323.
  • Zeng, Y. and Wu, S. eds., 2013. State-space models: Applications in economics and finance (Vol. 1). Springer Science & Business Media.
  • Zhang, G.P., 2003. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing, 50, pp.159-175.

Jeremy Kwok has experience working as a lead economist at a central bank and
at various financial institutions, with a background in engineering. He
works within the Autonomy Data Unit (ADU) as a doctoral researcher
(co-funded by Autonomy) focusing on nowcasting the UK economy.