I’ve been thinking about the economics issues that Tyler Cowen raises early in the last chapter of his marginalism monograph, “Why Marginalism Will Dwindle, and What Will Replace It?” An asset pricing model he discussed there had already precipitated me into a working paper of a methodological and philosophical nature, On Method: Computational Compressibility in Complex Natural and Cultural Phenomena, so that material was lurking in the background when I was watching a recent podcast by Kara Swisher and Scott Galloway. Galloway made a remark that resonated through that material: “Stocks are like brands and that is they’re part promise and part performance.”
That remark connected the assets in the pricing model, which are opaque to me, to things I’ve thought a great deal about, movies and novels. In that methodological paper I’d discussed Arthur DeVany’s work on Hollywood movies and Matthew Jocker’s work on the 19th century Anglophone novel. “If,” as Galloway remarked, “stocks are part promise and part performance, then, sure, they’re like moves and novels, too.” I made the connection on pure intuition.
I then turned to ChatGPT for help in explicating that intuition. So I issued another prompt into a dialog we’d had about those asset pricing models. I’ve appended that dialog below the asterisks.
NOTE that I have inserted the larger headings after completing the dialog. Pay particular attention to the italicized comment I inserted after this heading, “Brand as a distinct conceptual object.”
* * * * *
Stocks as Brands
I recently heard pundit Scott Galloway remark: “Stocks are like brands and that is they’re part promise and part performance.” Explicate that in terms of the discussion we’ve been having.
Galloway’s line is excellent for this discussion because it collapses the apparent distance between financial assets and cultural artifacts. A stock is not merely a claim on earnings. It is also a socially circulating promise about a future.
“Part performance” means the measurable side: revenues, margins, cash flow, debt, profitability, investment, growth, volatility, liquidity, analyst revisions, and so forth. These are the kinds of variables that show up among the 130 stock characteristics in the AIPT setup.
“Part promise” means the symbolic, anticipatory, collectively imagined side: what investors believe the company may become. Tesla is the obvious case: not just cars, but autonomy, energy, robotics, Elon-as-mythic-founder, technological destiny. Nvidia is not just current chip sales, but the promise of AI infrastructure. Apple is not just devices and services, but design trust, ecosystem lock-in, lifestyle aura, and continuity of desire.
That is exactly where stocks begin to look like brands, films, and novels.
A brand is a bundle of past performance plus future expectation. It has delivered something before, and that delivery authorizes a promise: “trust us again.” A stock works similarly. The firm’s past earnings, product history, management behavior, and market position generate a field of expectation. The price is not merely a summary of what the firm has done; it is an evolving collective judgment about what the firm will do.
In asset-pricing language, the “performance” side lives in observable characteristics and realized returns. The “promise” side lives in expectations, risk narratives, optionality, imagined futures, and the willingness of investors to pay now for possible future states. The pricing kernel/SDF is, in a sense, the market’s machinery for weighting those promised futures under uncertainty.
That is why low-dimensional factor models struggle. “Size,” “value,” “profitability,” and “momentum” capture pieces of performance and some traces of promise. But they do not capture the full cultural-cognitive ecology around an asset. The promise is distributed across analyst narratives, founder charisma, institutional herding, macro stories, technological imagination, regulatory fears, and the memory of past booms and crashes. That is a high-dimensional object.
Now compare movies. A movie before release is also part performance and part promise. The performance side includes director, stars, budget, genre, studio, opening screens, advertising. The promise side is what the audience imagines: “this will be the movie everyone talks about,” “this will give me the old Marvel feeling,” “this is the serious adult drama of the season,” “this is the date-night film.” De Vany’s “nobody knows” result follows because the promise cannot be validated until the social system responds. Word of mouth tests the promise.
Novels work the same way over longer historical time. A novel’s “performance” is its textual form: style, topic, genre, plot structure, diction, narrative technique. Its “promise” is the world of value, feeling, recognition, and possibility it offers its readers. Jockers’ 600-dimensional space captures formal and thematic performance, but the temporal diagonal suggests that the promise-world of novels changes over generations. Readers and writers inherit one horizon of expectation and then move it.
So Galloway’s remark helps unify the three domains:
A stock, a movie, and a novel are all promissory artifacts whose fate depends on how populations interpret prior performance as evidence for future value.
The difference is that financial markets price the promise continuously, movies test it sharply after release, and novels disclose it historically across generations.
This also helps explain why the AIPT result is so interesting. A 360,000-factor model is not simply “better math.” It is an attempt to approximate the high-dimensional geometry through which performance becomes promise and promise becomes price. That geometry is too rich for the old factors, just as the historical movement of novels is too rich for a few period labels, and the fate of movies is too rich for stars plus opening weekend.
So yes: stocks are like brands because they are not merely economic objects. They are expectational-cultural objects with cash-flow machinery attached. That is the brave-new-world point. Finance is not leaving culture behind; it is becoming analyzable by the same high-dimensional methods we need for culture.
Thus Galloway’s remark is very sophisticated. He has a podcast with Kara Swisher as well as a podcast (or two) of his own. Judging from his comments he’s a moderately wealthy man, and he made his money on his own. He comes from a modest background. I’d imagine that the comments he makes in his various public-facing venues are among the many signals that get incorporated into the judgments underlying the performances of the assets included in this high-dimensional models.
Yes. That is exactly the recursive loop.
Galloway is not merely commenting on the market from outside it. He is one of the many public-facing interpreters whose remarks enter the informational atmosphere in which assets are judged. His comments become part of the market’s semiotic environment: not hard data like earnings or cash flow, but signals that help shape collective expectations about firms, sectors, founders, brands, technologies, and macro direction.
That is where “stocks are like brands” becomes more than a metaphor. A brand is maintained by distributed talk: advertising, reviews, consumer experience, pundit commentary, memes, scandals, endorsements, complaints, jokes, status associations. A stock is maintained by a comparable but more formalized signal ecology: earnings reports, analyst notes, institutional flows, valuation models, regulatory news, founder behavior, social media, podcasts, CNBC hits, Substack essays, hedge-fund letters, Reddit chatter, and remarks by people like Galloway.
The AIPT model, strictly speaking, is not directly ingesting Galloway’s podcast transcripts. It begins with stock characteristics and then generates many nonlinear transformations of those characteristics into factors. But those characteristics are themselves downstream of an enormous informational process. Prices, momentum, volatility, analyst revisions, liquidity, profitability expectations, and valuation ratios already embody, in compressed form, the effects of countless judgments and signals. The paper’s model uses 130 stock characteristics and expands them into hundreds of thousands of nonlinear factors; that is a way of probing the market’s already-encoded collective cognition.
So, yes: Galloway’s public remarks are among the innumerable micro-signals that may influence the behavior of investors and analysts, which in turn affects price, volume, momentum, volatility, analyst expectations, and eventually the characteristic space that models like AIPT use. His comments may not be individually recoverable in the model, but they are part of the causal soup from which the measurable signals arise.
That also clarifies why his remark is sophisticated. He understands, probably from experience rather than formal theory alone, that markets are not just machines for discounting cash flows. They are machines for pricing credible stories about future performance. The credibility comes partly from past performance, but the price also reflects the market’s belief in the promise.
In our terms:
Performance becomes data.
Promise becomes expectation.
Expectation becomes price.
Price history and firm characteristics become model input.
Model output then feeds back into the interpretive environment.
That is the brave-new-world loop. Financial assets are no longer cleanly separable from culture. They are culturally mediated claims on future cash flows. Or, more compactly: stocks are narrative instruments with accounting attached.
Brands as
a cognitive bridge to culture (movies and novels)
Very interesting, especially for me. I know little about economics or about the stock market (and similar asset markets, e.g. commodities, currency). So these asset pricing models are very abstract indeed. But I know a lot about novels and movies and that gives me a way of grounding De Vany’s work and Jockers’ work. I’ve thought a lot about cultural evolution, and about complex dynamics. Thus their models make intuitive sense to me. Galloway’s remark, and your explication of it, gives me a way of grounding these otherwise opaque asset pricing models.
That is the productive move: you now have a cognitive bridge from a familiar domain to an unfamiliar one.
