New paper: Innovative Events

Anna and I have a new paper out in Research Policy. Publishing this has been an epic experience: six years in the making.

The TLDR; we introduce a brand-new measure of innovative activity — media-reported product and service launches — and run it through a series of key use cases.

Why is this important? We know innovation is important for economic growth. We also know it’s very hard to measure, and existing metrics — patents, trademarks, surveys — are all pretty limited.

A handful of studies have got around these limits by working with product-level data — typically in niche cases like pharma, where new products are regulated and very clearly defined.

We advance on this by building on Growth Intelligence data, which monitors ~3,000 online media sources across all industries. We do *a lot* of work in the paper to clean, rebuild and validate this info.

Our new metrics — reported launches of new products and services — cover all UK sectors and firm types. In the paper, we focus on SMEs to keep ascription as clean as possible.

We then do three things.

First, we show that these innovative events complement patents, trademarks and surveys — with higher frequency, wider industry and geographic coverage.

Next, we show that at the firm level, past IP predicts current launch activity. That is, if you filed patents or trademarks, that makes you more likely to launch a product down the line.

Finally, we show that launch activity helps explain variations in firm performance. A minority of firms with a high-profile launches drives this. That fits existing evidence on high-growth firms: a few stars drive overall growth.

Here’s the journal version again. You can also access the pre-print here, and play around with some of the data and code.

Last word: big thanks to Alex Coad and the reviewers at RP. Alex was a stern but kindly editor, whose suggestions made the paper a lot better.




UCL & CEP. Co-founder @centreforcities and @whatworksgrowth. Urbanism, economics, innovation, migration and public policy. My views. I’m at

Love podcasts or audiobooks? Learn on the go with our new app.

Recommended from Medium

Open Book: Qiang Zhu, Head of Data Science & Analytics

Metacritic Score Prediction for Video Games

Image Stitching to create a Panorama


The Upper Confidence Bound (UCB) Bandit Algorithm

RFM Customer Segmentation

Women in Power —Are Women Still Under-represented?

MLOps Level 0 — Manual Pipelines

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store
Max Nathan

Max Nathan

UCL & CEP. Co-founder @centreforcities and @whatworksgrowth. Urbanism, economics, innovation, migration and public policy. My views. I’m at

More from Medium

C’mon, we need to talk about IT, CEOs, and COOs

Mission Model or Business Model?

What are Probabilistic Programming Languages and why they might be useful for you

Our model consists of a categorical logit distribution for the discrete valued observations. The linear predictors for the probabilities of each of the categories depend on parameters beta. We assign a normal prior, of zero mean and standard deviation 5 to each element of the parameter vector beta.

The Unorthodox Approach to Job Titles that Makes Skills-based Recruitment Work