Guest Contribution: “Macroeconomic nowcasting in times of Covid-19 crisis: On the usefulness of alternative data”

Today, we are pleased to present a guest contribution written by Laurent Ferrara (SKEMA Business School and QuantCube Technology), Alice Froidevaux (QuantCube Technology) and Thanh-Long Huynh (QuantCube Technology).


Nowcasting macroeconomic activity has proved extremely useful to track in real-time fluctuations of macro aggregates like GDP, inflation, consumption … Indeed, Quarterly National Accounts are generally published on a quarterly basis by Statistical Institutes, with a delay of release of about one or two months. For example, to be aware of the economic activity in the first quarter of the year (from beginning of January to end of March), we need sometimes to wait until mid-May, depending on the country considered.

This is why nowcasting tools have been developed in order to be able to inform policy-makers and economic agents about the current state of the economy. As regards the U.S. economy, Atlanta Fed and New York Fed release on a regular basis estimates of current and future quarter-over-quarter GDP growth rate, expressed in annualized terms. Surprisingly, as March 25, 2020, the nowcast of Atlanta Fed for 2020q1 was of 3.1%, while it is clear today that the Covid-19 crisis is likely to have a strong impact on the economic activity in March, thus on Q1 (see previous Econbrowser posts here and here). The GDP nowcast from New York Fed was a bit lower at 1.49% as March 20, but still quite high.

How is that? In fact, all those nowcasting tools have been extremely well built but they only integrate official information, such as production, sales, surveys, that are released by official sources with a lag. Some price variables, such as stock prices that are reacting more rapidly to news, are also included in the nowcasting tools, but they do not strongly contribute to the indicator.

So how can we improve nowcasting tools to reflect high-frequency evolutions of economic activity, especially in times of crises? A solution is to investigate alternative data, that are available on a high-frequency basis. The multiplication in recent years of the number of accessible alternative data and the development of methods based on Machine Learning and Artificial Intelligence capable of handling them constitute a break in the way of following and predicting the evolution of the economy. Moreover, the power of digital data sources is the real-time access to valuable information stemming from for example multi-lingual social media, satellite imagery, localization data, textual databases, …

Let’s take the example of the Covid-19 crisis. On 9 January 2020, a man who had contracted COVID-19 died of a heart attack, becoming the first known death from the virus. On 13 January, the World Health Organization (WHO) reported the first known case outside China, a woman joining Thailand from Wuhan. The US reported the first death from the Covid-19 in the country, in the state of Washington, on 1rst March. A chronology of the events can be found in the CEPR e-book edited by Baldwin and Weder di Mauro (2020). Basically all the countries impacted started non-pharmaceutical interventions mainly based on social distancing. Against this background, the economic impact is expected to be quite strong and to generate a worldwide recession.

Within QuantCube Technology, we have put forward a nowcasting tool for U.S. GDP in real-time, by using various alternative sources of information such as (i) international trade of goods stemming from a daily tracking of ships around the globe, (ii) crude oil transportation also stemming from daily tracking of ships and (iii) a proxy of the job market created by aggregating the job offers per sectors available on websites. Those alternative data are available on a daily frequency without any publication lags and are combined with two sources of official information on household consumption (Personal Consumption Expenditures) and on consumer sentiment (University of Michigan). The composite index is presented below and aims at tracking year-over-year U.S. GDP growth.

Figure 1: U.S. Economic Growth Index tracking the year-over-year growth rate of U.S. GDP in real-time (Source: QuantCube Technology).

We clearly see that this index is able to efficiently track U.S. GDP growth in real-time (correlation of 0.75), especially as regards peaks and troughs in the cycles. For example, focusing on the year 2016, we observe that the index anticipated the slowing pace of the U.S. economy for this specific year which was the worst year in terms of GDP growth since 2011, at 1.6% annually. More recently, the index pointed out the deceleration of the U.S. economic activity starting from mid-2018, amid escalating trade tensions with the U.S. and rising global uncertainties.

Focusing on the latest data, the US nowcast for 2020q1 stands at 0.80% on 25 March 2020, consistent with a quarter-over-quarter GDP growth of about -3.0% in annualized terms. The U.S. recession is likely to be unavoidable.

Those massive alternative data have the great advantage of being available at a very high frequency, thus leading to signals that can be delivered well ahead of official data. Also, those data are not revised, avoiding thus a major issue for forecasters. However, there is no free lunch.  An important aspect that is not often considered in empirical works is related to the cleaning of raw data. Indeed, it turns out that unstructured raw data are often polluted by outliers, seasonal patterns or breaks, temporary or permanent.  For example, when dealing with daily data, they can present two or more seasonalities (e.g. weekly and annual).

 


This post written by Laurent Ferrara, Alice Froidevaux, and Thanh-Long Huynh.

37 thoughts on “Guest Contribution: “Macroeconomic nowcasting in times of Covid-19 crisis: On the usefulness of alternative data”

  1. Moses Herzog

    WOW, this blog post is a treasure trove for the CEPR book download alone. Gopinath might take this more personal than most because she went to University in Washington. I thought I remembered Menzie saying he had relatives around Seattle?? Maybe I just made that up in my own head because I now there’s a large Asian contingent there. Well, anyways…… if you got any family/friends in the 55+ age range in Washington state it’s a time of mild angst at the very least.

    1. WIllie

      I live in Seattle and both my wife and I are over 55. As are many of our friends. It is a strange time here. Downtown is the zombie apocalypse, with very few people out and about, and those who are out and about are generally disheveled street people who have nowhere else to go. Supermarkets are open, and people are keeping physical distances between each other for the most part. There are no weird rumors floating around so far as I know. It’s all bizarrely peaceful. Flowers are blooming, with more flowers on the way. Seattle’s neighborhoods are vibrant with flowers in the spring. That will remain true no matter what else happens. Very few people are out on the sidewalks in the residential neighborhoods. It is strange, but I’m more concerned about the survival of local businesses whose operators I consider neighbors and friends. We are isolating, which makes the likelihood of infection far smaller than it would be. We may be isolating for most of April unless something changes. Famous last words, but it seems like this area is no longer quite the hot spot it once was, at least by grim comparison. It’s bad, the system is strained at best, and we are certainly taking it seriously. I don’t know that we have turned a corner yet. Maybe in a week or two. That’s not very long in the grand scheme of things.

      1. pgl

        The good news may be that Washington State may have finally started on the down side of that curve. I doubt all will be well for you guys by Easter as The Idiot in Chief thinks. Here is New York, our doctors are saying we need 40 thousand ventilators to handle our sick elderly patients. Now the Idiot in Chief is sending a few hundreds as of course he “knows” are doctors are not correct. In the meantime, people are dying in our hospitals. I’ll get others decide who is right here – our doctors or the Idiot in Chief.

        1. Willie

          The general consensus that I see is that Washington State will peak in mid to late April and then taper off. Turning a corner, in my mind, is seeing the rate of increase start to taper. Then we will turn another corner when the caseload starts to fall. I don’t expect that to happen for months. This is going to be a grind, but it a short grind relative to being dead. I’m baffled about how the polls could show positive overall opinions of Trump’s performance so far. It is still early, in spite of how long this feels like it has been going on.

          1. Baffling

            Trump has positive polls because faux new still downplays the severity of the virus, and promotes the idea that we have responded well. We are the single largest source of virus now, and in about a week we will also have the most deaths. But faux news continues to say we had the best response worldwide, and will continue to tell its viewers this even as the virus kills them off in particular.

          2. Barkley Rosser

            Baffling,

            All leaders in nations with lots of the virus have seen their poll ratings rise. However, while Trump’s have risen by about 5%, people like Macron and Conte and Merkel have all seen theirs rise in excess of 20%. It is simply natural for people to “rally round the national leader in a crisis” even when the national leader is not doing all that good of a job. But Trump is only getting a minimal bump compared to these other national leaders.

          1. pgl

            Cuomo understands this ventilator issue and tells the truth. Trump? An idiot and a liar at the same time.

            What caught my attention was that 20 day need per patient for a ventilator. Here is what is interesting about Gilead Sciences phase III trials on Remdesivir. If this works and to the degree production can be ramped up, patients who take this for 5 days can safely get off the ventilator.

            Odd Trump mentions a lot of pipe dreams which his sycophant Bruce Hall goes off on but he does not mention Gilead Sciences. I guess Gilead’s CEO has not sent Trump any love or campaign contributions.

      2. Moses Herzog

        @ Willie
        The good thing is, I think Seattle tends to be a more literate, better educated, and better informed city (speaking generalities here). Ironically that includes the Asian community, which probably was hit due to visiting family. But, I think a better educated populace makes for a better fight. In your age group I think you should be generally “concerned” but not “worried”. Anyways my thoughts and prayers are with you.

        The New Orleans mayor royally failed her citizenry. I don’t see issues such as that occurring in Seattle or your splendid state.

        1. Willie

          I do not know the ethnicity of the traveler who brought the virus here. I doubt the virus knows, either. There is a whole lot of travel and commerce between Seattle and parts of China. And the rest of Asia. It could have come here with almost anybody, and probably more than one person.

          As I recall mentioning, I play cymbals made in Wuhan. The company that imports them is Canadian. People from the western US and Canada have various business and personal ties to China.

          This disease puts the lie to nationalism and isolationism, because it respects neither.

          1. Moses Herzog

            It cannot be said with certainty, however you would have to allow if we are considering probabilities, it most apt started in Washington by a Chinese American who travelled to China, was exposed, and then came back. It is an incredibly big coincidence to have that start in a city with a larger Chinese contingent than most other cities. That is no “scarlet letter” on the person who did it and should not be ANY source of shame for the person who unknowingly transmitted it. I am just stating that as a pragmatic reality.

          2. Baffling

            Moses you must be wrong. Trump shut down the border with china early on. He said so himself. Probably caused by a mexican crossing the border in seattle.

  2. AS

    Question for QuantCube Technology.

    Looking at your website, I did not see the pricing for GDP data above.

    1. Moses Herzog

      It may be “proprietary” information. I’m not certain on that, but it’s a good guess. That’s no “sin” on their part. But I am a believer in open information. But no doubt there are costs in their technology equipment and “scrounging” for the data. So it’s hard to argue too strongly they should not get some “remuneration” on that. And I’m the type to whine and complain on that stuff being out of reach. But I think here….. I have mixed feelings but I think I can give them “a pass” this time.

    2. Ghizlaine Amrani

      Thank you for sharing your comment. Quantcube is a Fintech Company specialized in Alternative Data Analytics for Economic Intelligence. We provide real-time indices of major macroeconomic variables such as economic growth, employment market, inflation, international trade or consumer expenses.
      Should you have any question or need further information about pricing, please feel free to contact us at [email protected]

  3. pgl

    I’ve been following the spread on corporate bonds rated BBB by S&P (the long-term corporate bond yield minus the long-term government bond yield). This spread hit 3.8% last Friday and seems to have stayed there. Not quite as bad as after the collapse of Lehman Brothers but still very high.

    1. Moses Herzog

      @ pgl
      The Fed Res promise of purchasing bonds to infinitum probably has some relationship to that 3.8% not moving much.

      Strange how that money always pops up for the wealthy cats who own bonds. Don’t expect any announcements on residential mortgage terms as they “don’t have the money for that“. Not to mention “the importance of contract law”.

    1. pgl

      Oh Lord – you are worse than even Bruce Hall for babbling without reading your own links. Sure they can spot people having mass parties by excact location which of course helps identify the self absorbed jerks spreading COVID 19 without a care in the world. But neither one of your links indicates a street by street measure of gross domestic product. Oh wait – you thought GDP stood for some potential COVID 19 treatment. Got it!

    2. Steven Kopits

      The data is there. But you need to know how to process it. This is what econ departments should be teaching. Econometrics is fine, but what does it mean when you can circle locals on a map? How do we make sense of that? It requires the development of whole new disciplines, not displacing traditional econometric methods, but building on them with additional tools.

      I would add that some of this data is expensive. The US government should make it available, certainly to the likes of the Fed, but also to academics. We have far greater data and analytical capability than is commonly appreciated, and the Fed should not have to go begging to get the funding to access these various data sources. It is frankly appalling that the guys at GDPNow and the Nowcast do not have access to near real time global signals data, for example, mobile phone data via Tectonix. They should not be a kind of skunk works, but rather the repositories of the glories of analytics at our central bank.

  4. Alan Goldhammer

    I’m not conversant with the economic modeling literature. Has any one modeled what would have happened to the economy had the US done nothing. I’m not interested in ICU and hospital problems as that was evident based on the Italy experience and the principal reason for the ‘social distancing’ lock downs is to moderate utilization of ICUs.
    What interests me is the rate of employee absenteeism and general business slow down that would result from this. My intuition is that there would have been an adverse impact on the US economy but how much?

    1. macroduck

      I’m not aware of any estimates for an alternative future in which nothing was done to slow the spread, but there is work on what happened to the economy in various regions during the 1918 pandemic, based on the level of effort to slow the spread:

      https://papers.ssrn.com/sol3/papers.cfm?abstract_id=3561560

      The conclusion is that non-drug intervention reduces deaths and improves economic outcomes.

      1. Alan Goldhammer

        @Willie – yes, I’m aware of the adverse impact of death 🙂
        @macroduck – thanks, I’ll give that paper a read

    2. Steven Kopits

      It’s a moot point. Sooner or later, the population would have hunkered down, with or without the government.

      1. Baffling

        Yes steven, but without intervention and isolation the eventual hunkering down, while temporary, would have coexisted with significant permanent losses due to death. Temp vs permanent must be distinguished.

        1. Steven Kopits

          The government plays an important role in timing, I agree. For example, if we are 14 days behind Italy, then we should see something about 750,000 confirmed cases. If 21 days behind, 2.75 million cases. One week equals a factor of four. Both lock-downs are temporary as such, but the effects are vastly different with just a few days difference in timing.

          1. baffling

            steven, the growth is exponential. and if lockdown is effective, you will not simply see a lag and similar pattern form. the primary purpose of a lockdown early on is the it can severely restrict community transfer of the virus going forward. you do not necessarily get the same inevitable outcome, just further out in time. if you lock down early enough, you stop the spread-period. if you lock down too late, or with to little enforcement, you get spread-perhaps slow-throughout the entire population. that is italy. we had an opportunity to lock down and stop the spread like china did. we missed that opportunity while the administration dorked around. trump was more concerned about the economy, and his own political future, than stopping the virus cold. people on this blog simply referred to it as the flu. by the time the population decides to hunker down itself, you cannot contain, only somewhat slow the spread. unfortunately that is where we are. as you said steven, timing makes a big difference. but in a way that is different than what you were insinuating. we could have been china rather than europe.

  5. Moses Herzog

    Am I crazy or does this make Darrel look like he’s driving a little fast?? OK< never mind the first question, is Darrel driving to fast?? See if that load is heavy it may shift on him going around some of those corners….. I think. Second opinions??
    https://www.nytimes.com/2020/03/28/us/coronavirus-truckers.html?action=click&module=Top%20Stories&pgtype=Homepage

    These are some of the people who keep this nation running….. when the nation is not running. They deserve your respect. See if you can force and/or cajole it out of yourself next time you see a truck driver who looks like he/she hasn’t showered for 3 days.

  6. Moses Herzog

    These are the ones that really grab my attention.
    https://www.theguardian.com/world/live/2020/mar/29/coronavirus-live-news-trump-proposes-quarantine-of-new-york-and-other-hotspots?page=with:block-5e804e168f081e5eda238d93#block-5e804e168f081e5eda238d93
    I’ll confess, some of the news, I’m not saying I don’t care, it just starts to kinda wash over you with the volume right?? And I don’t wanna say “numb”, but your mind gets…. “dulled” (???) to the news?? I’m just trying to be honest here on how I internalize most of it. But you read this, she’s 33….. that one catches my attention. So then you wonder “Hmmm….what was the deal on that one??”. It could be something as simple as she had asthma most her life. It could be she was a chain smoker. It could be in fact a very simple thing. But until you know, it kind of jolts you.

  7. baffling

    ““If they don’t treat you right, I don’t call,” the president said.”
    this is what the president said to the states. if you don’t kiss my ass, i won’t help you. so to all you conservatives-rick stryker, corev, bruce hall, peak loser, etc-remember this time period in time. the conservative president is willing to kill citizens of the usa if proper patronage is not paid to king trump. you ALL should be ashamed by the performance of this idiot in chief. embarrassing. and i won’t let you forget your endorsement of this killing machine.

    1. Moses Herzog

      @ baffling
      Our judges say that is a 5-star comment.

      Some people will say your comment is too acerbic. If I could give you a solid gold medal for that comment, I promise you I would. You dead on hit the target, and anyone who had any doubts up to now (hard to believe they are out there, yet……) that the orange creature is a 100% amoral bastard, the impeccable illustration you made in your comment would be the Sean Kemp slam dunk on that question.
      https://youtu.be/HQeMhYJe5JA?t=38

  8. Moses Herzog

    Joe Diffie was born in Tulsa Oklahoma, spent time as a young man in the states of Oklahoma, Washington, and Wisconsin. He attended Cameron University in Lawton Oklahoma (a school I lived near and spent many a summer day and weekend biking around the campus). He worked in oil fields in Texas. Had five #1 singles on the Billboard country charts. For roughly 10 years Diffie had a charity concert and golf tournament to benefit the education of mentally and physically impaired children. He died in Nashville, only two days after making public he had COVID-19. Joe Diffie was 61. Survived by 5 children from different wives (if I counted it right)
    https://www.youtube.com/watch?v=vMiEFyTuuh8

Comments are closed.