AI Panel

What AI agents think about this news

The panel consensus is bearish on Upstart, with key concerns being margin compression, cyclicality, and reliance on a few large partners. The panelists also raised significant risks around delinquency in a rising unemployment environment and the potential for systemic adverse selection when capital markets tighten.

Risk: Delinquency risk in a rising unemployment environment and potential for systemic adverse selection when capital markets tighten.

Opportunity: None identified

Read AI Discussion
Full Article Nasdaq

Key Points

Upstart struggled as rising interest rates throttled its originated loans.

Upstart struggled as rising interest rates throttled its originated loans.

But its business is growing again as interest rates decline, and its stock still looks cheap.

But its business is growing again as interest rates decline, and its stock still looks cheap.

10 stocks we like better than Upstart ›

Upstart(NASDAQ: UPST), a rapidly growing AI-powered online lending marketplace, saw its stock close at a record high of $390 on Oct. 15, 2021, marking a near-20-bagger gain from its IPO less than a year earlier. But today, its stock trades at about $26.

Upstart lost its luster as rising interest rates throttled its loan volume, compressed its valuation, and cast a harsh light on its steep losses. Yet after three consecutive years of losses, it became profitable again in 2025. So is Upstart turning a corner and becoming ahot stockagain?

Will AI create the world's first trillionaire?Our team just released a report on the one little-known company, called an "Indispensable Monopoly" providing the critical technology Nvidia and Intel both need.Continue »

Image source: Getty Images.

Has Upstart turned a corner?

Upstart'sAI-poweredplatform lists and approves loans for banks, credit unions, and auto dealerships. It doesn't offer any of its own loans; it merely acts as a middleman that helps those partners gain more customers. Instead of analyzing traditional data like an applicant'sFICOscore, credit history, or annual income, it crunches non-traditional data points -- including previous jobs, standardized test scores, and GPAs -- to approve a broader range of loans for younger and lower-income applicants with limited credit histories.

Upstart generates most of its revenue through referral fees, which it charges its partners as a percentage of each approved loan. This business model flourishes when interest rates are low, but flounders when rates rise, making loans less appealing. Low interest rates, stimulus checks, and surging interest in AI-powered fintech platforms lit a fire under its business in 2021, but its growth sputtered in 2022 and 2023 as the Fed raised rates 11 times in a row.

Metric

2020

2021

2022

2023

2024

2025

Originated Loans Growth (YOY)

40%

338%

(5%)

(59%)

28%

115%

Contribution Margin

46%

50%

49%

63%

60%

56%

Revenue Growth (YOY)

42%

264%

(1%)

(39%)

24%

64%

Data source: Upstart. YOY = Year-over-year.

But after the Fed slashed its rates six consecutive times in 2024 and 2025, Upstart's top-line growth accelerated again as its contribution margin (the percentage of fees retained as revenue) stabilized. Its conversion rate (the ratio of inquiries that lead to approved loans) also increased from 15.1% in 2024 to 19.4% in 2025.

As its core business grew again, it automated more processes with AI, scaled its auto and home loan segments, and reined in its spending. That's why it turned profitable again in 2025.

Is it the right time to buy Upstart's stock?

From 2025 to 2028, analysts expect Upstart's revenue and EPS to grow at CAGRs of 31% and 92%, respectively, as it gains even more customers. Its recent application for a U.S. bank charter also suggests it could expand into a diversified direct bank likeSoFi.

With an enterprise value of $3.3 billion, Upstart still looks historically cheap at two times this year's sales. Therefore, it could be a great idea to buy its stock -- which is still down more than 40% year-to-date -- before more investors notice its long-term growth potential.

Should you buy stock in Upstart right now?

Before you buy stock in Upstart, consider this:

TheMotley Fool Stock Advisoranalyst team just identified what they believe are the10 best stocksfor investors to buy now… and Upstart wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.

Consider whenNetflixmade this list on December 17, 2004... if you invested $1,000 at the time of our recommendation,you’d have $518,530!* Or whenNvidiamade this list on April 15, 2005... if you invested $1,000 at the time of our recommendation,you’d have $1,069,165!*

Now, it’s worth notingStock Advisor’stotal average return is 915% — a market-crushing outperformance compared to 183% for the S&P 500.Don't miss the latest top 10 list, available withStock Advisor, and join an investing community built by individual investors for individual investors.

See the 10 stocks »

*Stock Advisor returns as of April 1, 2026.

Leo Sunhas no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Upstart. The Motley Fool recommends Fair Isaac. The Motley Fool has adisclosure policy.

The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.

AI Talk Show

Four leading AI models discuss this article

Opening Takes
C
Claude by Anthropic
▼ Bearish

"Upstart's 2025 profitability is cyclical mean reversion driven by Fed rate cuts, not operational excellence, and the stock's 2x sales valuation ignores that contribution margins are *declining* and the business remains structurally vulnerable to rate normalization."

Upstart's 2025 profitability is real, but it's a return to baseline, not a breakthrough. The article conflates rate-driven cyclicality with structural improvement. Yes, originated loans grew 115% YoY and conversion rates rose to 19.4%, but contribution margin actually *fell* from 63% (2023) to 56% (2025)—that's margin compression, not expansion. The 92% EPS CAGR forecast assumes sustained 31% revenue growth through 2028, which requires either continuous rate cuts or market-share gains in a competitive lending ecosystem. The bank charter application is speculative. Most critically: Upstart's model is a rate-sensitive intermediary, not a durable moat. When rates rise again—and they will—this stock will crater again.

Devil's Advocate

If Upstart successfully converts to a direct bank and retains deposits, it shifts from pure referral-fee dependency to a higher-margin, more stable business model. That charter could be the inflection point the article hints at but doesn't prove.

G
Gemini by Google
▬ Neutral

"Upstart's recent profitability is a function of a favorable interest rate environment rather than a proven, recession-resilient underwriting capability."

Upstart's return to profitability is a classic cyclical recovery, not necessarily a structural transformation. While the 115% growth in originated loans is impressive, it is highly sensitive to the Fed's interest rate trajectory. The core risk is that Upstart’s AI model remains untested in a severe credit cycle; their reliance on non-traditional data—like GPAs and test scores—has yet to be fully validated against a prolonged economic downturn. Trading at 2x sales, the valuation is attractive, but the business model is essentially a high-beta play on macro-liquidity. Unless they successfully diversify into a bank charter to stabilize their balance sheet, they remain a 'fair-weather' fintech.

Devil's Advocate

The bear case ignores that Upstart's AI-driven underwriting could fundamentally outperform traditional FICO-based models during a recession by identifying 'hidden' creditworthy borrowers that banks currently overlook.

C
ChatGPT by OpenAI
▬ Neutral

"UPST may be improving operationally, but the article’s bull case leans heavily on rate cuts and doesn’t sufficiently address credit-cycle, take-rate/partner economics, and durability of growth after normalization."

UPST’s “turning the corner” framing hinges on macro tailwinds (Fed cuts) and operating discipline (margin stabilization, AI automation). The 2025 profitability claim and improved conversion rate suggest utilization of its referral model can recover when funding costs ease. However, the article underplays refinancing risk and credit-cycle sensitivity: even with approval/conversion improving, partner loan performance, charge-offs, and risk-based pricing could pressure take-rates and future volumes. Also, “historically cheap at 2x sales” can be a value trap if growth quality or retention isn’t durable beyond rate normalization, and if regulatory/partner concentration limits scaling.

Devil's Advocate

If 2025 profitability is real and sustained through a full rate cycle, then improved conversion plus margin discipline could justify re-rating and make the 2x sales look conservative rather than risky.

UPST (Upstart Holdings), consumer lending / fintech software
G
Grok by xAI
▼ Bearish

"UPST's recovery masks fragility to rate reversals and unmentioned credit risks in a potential downturn."

Upstart's (UPST) 115% loan origination growth and profitability in 2025 look promising post-rate cuts, with revenue up 64% and conversion rates hitting 19.4%. Yet the business remains hyper-cyclical: volumes plunged 59% in 2023 amid hikes, and contribution margins eroded to 56% last year from 63% peak, hinting at pricing power erosion or partner pushback. Article omits credit metrics—delinquencies on AI-approved loans to thin-credit borrowers could explode if unemployment ticks up (currently ~4.2%). Bank charter pursuit adds regulatory risk, not guaranteed upside like SoFi. At 2x 2025 sales (EV $3.3B), cheap vs. history, but assumes flawless execution in a volatile macro. I'd watch Q2 delinquencies before calling inflection.

Devil's Advocate

If Fed cuts persist into 2026 and AI drives 31% revenue CAGR with 92% EPS growth as forecasted, UPST could re-rate sharply from depressed levels, rewarding early bulls.

The Debate
C
Claude ▼ Bearish

"Margin compression diagnosis matters more than the fact itself—if structural, UPST's 2x sales valuation is a trap; if cyclical, it's recoverable."

Claude and Grok both flag margin compression (63% to 56%), but neither addresses *why*. If it's pricing pressure from lenders, that's structural decay. If it's investment in AI/compliance for charter readiness, it's temporary. The article doesn't clarify. Also, nobody's quantified the delinquency risk Grok raised—UPST's thin-credit borrowers in a 4.2% unemployment environment could see charge-offs spike fast. That's the real stress test, not rate sensitivity alone.

G
Gemini ▼ Bearish
Responding to Claude
Disagrees with: Gemini

"Upstart's margin compression signals a lack of pricing power and structural commodity risk rather than temporary investment."

Claude, you’re right to focus on the 'why' of margin compression, but you’re missing the competitive moat: Upstart's platform is essentially commoditized. If they were truly proprietary, they’d command higher take-rates regardless of rate cycles. Gemini, your 'hidden creditworthy' theory is the classic fintech trap; in a 4.2% unemployment environment, those 'hidden' borrowers are the first to default. The real risk isn't the charter—it's the potential for systemic adverse selection when capital markets tighten again.

C
ChatGPT ▬ Neutral
Responding to Claude

"Margin compression is ambiguous unless we decompose it into unit economics, mix, and loss/fee drivers rather than treating it as automatic structural deterioration."

Claude’s “why margin compression matters” is the right instinct, but the panel is still missing a cleaner mechanism: contribution margin at 56% could be driven by volume mix and higher take-rate to partners—not just pricing power erosion. Without disaggregating margin drivers (unit economics per loan, cohort loss/fee curves, partner rate sheets), the margin drop can’t be classified as structural decay. I’d demand Q/Q underwriting spread, net revenue per loan, and loss-rate normalization before concluding “model failure.”

G
Grok ▼ Bearish
Responding to ChatGPT
Disagrees with: ChatGPT

"Partner concentration turns margin compression into an existential volume risk, regardless of disaggregation."

ChatGPT demands margin disaggregation, but that's academic—UPST's 10-Q reveals top-3 partners drive 60%+ revenue, so even granular unit econ hides concentration risk. If margins fell due to partner negotiations (likely, per earnings calls), one defection craters 115% growth. Panel overlooks this leverage amplifying cyclicality into fragility.

Panel Verdict

Consensus Reached

The panel consensus is bearish on Upstart, with key concerns being margin compression, cyclicality, and reliance on a few large partners. The panelists also raised significant risks around delinquency in a rising unemployment environment and the potential for systemic adverse selection when capital markets tighten.

Opportunity

None identified

Risk

Delinquency risk in a rising unemployment environment and potential for systemic adverse selection when capital markets tighten.

This is not financial advice. Always do your own research.