By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel's net takeaway is that Oracle's massive cloud growth and backlog are promising, but the company's heavy reliance on a few mega-contracts, negative free cash flow, and significant debt raise plans in 2027 pose substantial risks that could outweigh the potential rewards.
Risk: The single biggest risk flagged is the potential for customer default or project delays, which could lead to a leverage trap and force Oracle to raise more capital at worse valuations.
Opportunity: The single biggest opportunity flagged is the structural AI demand that exceeds prior forecasts, which could drive significant revenue growth if executed successfully.
This analysis is generated by the StockScreener pipeline — four leading LLMs (Claude, GPT, Gemini, Grok) receive identical prompts with built-in anti-hallucination guards. Read methodology →
Oracle's fiscal fourth-quarter revenue rose 21%, helped by 93% growth in cloud infrastructure.
Remaining performance obligations soared to a record $638 billion.
The company plans to raise about $40 billion in fiscal 2027 to help fund its data center build-out.
Oracle (NYSE: ORCL) reported its results for the fiscal fourth quarter of 2026 (the period ended May 31) after the market closed on Wednesday, and by most measures, the report was excellent. Revenue rose 21% year over year to $19.2 billion, and the company's backlog of contracted future revenue swelled to a record $638 billion. Management also stood by its forecast for revenue to reach $90 billion in fiscal 2027 -- growth of about 34%. Yet shares of the cloud and database giant slipped about 7% in after-hours trading as of this writing.
So why would investors sell on numbers like these?
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 »
Part of the market's concern seems to center on what all of this growth costs. Oracle said it plans to raise about $40 billion in fiscal 2027 to help fund its artificial intelligence (AI) data center build-out -- on top of the $48 billion of debt and equity it raised in fiscal 2026.
Here's a closer look at the quarter, including the heavy spending required to make it happen.
Oracle's cloud infrastructure business, which rents out computing power (much of it used for AI training and inferencing) once again drove the results. The segment's revenue rose 93% year over year to $5.8 billion in the fiscal fourth quarter. And the quarter-to-quarter trend is arguably as impressive as the headline number. From 55% to 68% to 84% and now 93%, the segment's year-over-year growth rate accelerated in every quarter of fiscal 2026.
Total cloud revenue, which combines cloud infrastructure with the company's cloud applications, grew 47% to $9.9 billion.
And Oracle's profitability was notable, too. Its non-GAAP (adjusted) earnings per share rose 24% to $2.11. Even after excluding some one-time investment gains during the period, adjusted earnings per share grew 20%.
Then there's the backlog.
Oracle's remaining performance obligations (RPO) (contracted revenue the company hasn't yet delivered) grew by $85 billion in the quarter alone to $638 billion. Showing how staggering this figure is, the figure stood at about $138 billion a year earlier. And the backlog should start turning into revenue at a faster pace, with chief financial officer Hilary Maxson saying during the fiscal fourth-quarterearnings callthat Oracle expects to recognize about 12% of its RPO as revenue over the next 12 months.
Management expects the momentum to continue, guiding for total cloud revenue to grow between 57% and 63% in constant currency in the fiscal first quarter of 2027. And CEO Clay Magouyrk said during the call that Oracle plans to bring nearly a gigawatt of computing capacity online in the current quarter -- about as much as the company added during all of fiscal 2026.
But building data centers at this pace is extraordinarily expensive.
Oracle's capital expenditures totaled $55.7 billion in fiscal 2026 -- more than two and a half times what it spent a year earlier. So even though the company's operating cash flow jumped 54% to $32 billion, free cash flow for the year was negative $23.7 billion.
To support these capital expenditures, Oracle raised $43 billion in debt and $5 billion in equity during fiscal 2026, and its interest expense for the year climbed 29% to $4.6 billion.
Notably, the roughly $40 billion the company plans to raise in fiscal 2027 includes its previously announced $20 billion at-the-market equity program (a plan to gradually sell newly issued shares, which dilutes existing shareholders).
Customers are helping shoulder some of the load, however. Oracle said the prepaid and customer-supplied hardware portions of its large AI contracts now total $75 billion.
"This substantially reduces the amount of capital Oracle must raise to build out our AI datacenters," the company said in its fiscal fourth-quarter earnings release.
Still, most of the recent backlog growth came from a small number of enormous AI contracts, including a reported $300 billion, five-year agreement with OpenAI signed last year. The ChatGPT maker reportedly remains unprofitable, and it filed confidential paperwork for an initial public offering just days before Oracle's report. If a customer of that size were ever unable to pay for the computing it has contracted, a meaningful piece of Oracle's backlog may never become revenue.
So, what should investors make of the pullback?
Following the after-hours dip, the stock's forward price-to-earnings ratio sits at about 24. For a company growing this quickly, that valuation arguably looks reasonable.
I think the market's hesitation is understandable, though. Oracle is borrowing and issuing stock at a scale few companies ever have, and the payoff depends on customers honoring some of the largest contracts in the technology industry's history. The demand is clearly there. But until free cash flow returns to positive territory, the stock could remain volatile. After all, when a company spends this aggressively, investors may want more proof before paying up for the growth.
Before you buy stock in Oracle, consider this:
The Motley Fool Stock Advisor analyst team just identified what they believe are the 10 best stocks for investors to buy now… and Oracle wasn’t one of them. The 10 stocks that made the cut could produce monster returns in the coming years.
Consider when Netflix made this list on December 17, 2004... if you invested $1,000 at the time of our recommendation, you’d have $439,038! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,277,804!
Now, it’s worth noting Stock Advisor’s total average return is 942% — a market-crushing outperformance compared to 206% for the S&P 500. Don't miss the latest top 10 list, available with Stock Advisor, and join an investing community built by individual investors for individual investors.
**Stock Advisor returns as of June 10, 2026. *
Daniel Sparks and his clients have no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Oracle. The Motley Fool has a disclosure policy.
The views and opinions expressed herein are the views and opinions of the author and do not necessarily reflect those of Nasdaq, Inc.
Four leading AI models discuss this article
"Oracle's enormous backlog and aggressive capex are unsustainable without a path to positive free cash flow and deleveraging, creating meaningful downside risk to the stock."
Oracle delivered solid quarterly growth, led by 93% cloud infra revenue and a record $638B RPO, with a roadmap to $90B revenue in fiscal 2027. Yet the core truth for bulls/ bears is the funding risk: a $40B debt/equity raise in 2027, plus a $20B ATM, to finance a data-center spree that already produced negative free cash flow in 2026. The backlog is heavily skewed by mega contracts (notably OpenAI) and 12% of RPO to revenue next year may still imply high execution risk if customers push back or project delays hit margins. Valuation at ~24x forward earnings looks reasonable only if FCF returns to positive and leverage stabilizes.
The bull case: the AI compute cycle is secular, and mega deals like OpenAI may prove durable revenue engines, allowing utilization ramps to lift cash flow and justify high multiples if financing costs stabilize.
"Oracle is trading future equity value for current infrastructure spend, making the stock highly sensitive to the credit risk of its largest AI customers."
Oracle's fiscal 2026 results reveal a massive pivot from a legacy software firm to a capital-intensive AI utility. While the $638 billion RPO is eye-catching, the market is rightfully fixated on the negative $23.7 billion free cash flow. Oracle is effectively levering its balance sheet to bet on the solvency of hyperscalers and AI startups like OpenAI. At a 24x forward P/E, you are paying for hyper-growth, but the dilution risk from the $40 billion capital raise in 2027 creates a structural ceiling for the stock. Until Oracle proves it can self-fund this infrastructure, the 'backlog' is more of a liability-backed promise than a cash-flow engine.
If Oracle’s massive capital expenditure creates an insurmountable moat in cloud capacity, their pricing power will eventually lead to massive margin expansion that justifies the current debt-fueled dilution.
"Oracle's backlog is only valuable if customers remain solvent and the company survives negative free cash flow for 2-3 more years—a bet on both execution and macro stability that the market correctly priced as risky."
Oracle's 93% cloud infrastructure growth and $638B backlog are real, but the 7% post-earnings drop reflects a legitimate solvency concern the article downplays. Free cash flow of -$23.7B in FY2026 is not a temporary capex trough—it's structural. The company is now burning cash faster than it generates it while servicing $4.6B annual interest on ballooning debt. The $75B in customer prepayments masks a critical vulnerability: if even one mega-contract (OpenAI's reported $300B deal with an unprofitable customer) faces payment stress, Oracle's backlog-to-revenue conversion breaks. The 24x forward P/E assumes flawless execution and customer solvency through a multi-year capex cycle.
If Oracle's capex peaks in FY2027 and cloud margins expand as scale improves, free cash flow could turn positive by FY2028, justifying current multiples and making the 7% dip a buying opportunity for patient investors.
"93% sequential cloud infra acceleration plus $75B customer-funded hardware validates capex intensity more than the article credits."
Oracle's 93% cloud infrastructure acceleration to $5.8B and $638B RPO (up $85B in one quarter) point to structural AI demand that exceeds prior forecasts. The $75B in customer prepayments offsets roughly half the planned $40B 2027 raise, while 12% RPO conversion guidance implies visible revenue ramp. Forward P/E near 24x against 34% 2027 revenue target remains undemanding if free cash flow turns positive by fiscal 2028. Risks center on execution of gigawatt-scale builds and concentration in a handful of contracts rather than broad dilution fears.
Even with prepayments, a single large customer default or delayed IPO (OpenAI) could erase 40%+ of incremental backlog, and sustained negative FCF plus ongoing equity issuance may compress multiples below 20x before growth materializes.
"The bigger overlooked risk is refinancing: high-rate funding for the 2027 $40B raise plus a $20B ATM could blow up cash burn and push multiples lower if credit remains tight."
To Grok: I agree concentration risk matters, but OpenAI only erasing 40%+ of incremental backlog assumes static terms; Oracle could reallocate capacity and monetize more customers as it scales. The far bigger overlooked risk is refinancing cost. Even with $75B in prepayments, Oracle plans a $40B 2027 raise plus a $20B ATM to fund capex. If rates stay high or credit tight, funding costs could explode, pushing cash burn longer and pressuring multiples.
"Oracle's primary risk is operational execution in power/cooling infrastructure rather than the creditworthiness of its hyperscale customers."
Claude, you’re missing the shift in Oracle’s leverage profile. While you focus on the $23.7B FCF burn, you ignore that Oracle is essentially acting as a project finance vehicle. The $75B in prepayments isn't just 'masking' risk; it’s non-recourse capital that effectively de-risks the build-out. The real danger isn't customer default—it's the operational bottleneck of power and cooling. If they can't get the gigawatts online, that $638B RPO becomes a massive litigation liability, not revenue.
"Operational delays matter more than binary default risk because they extend negative FCF and accelerate dilution timing, not magnitude."
Gemini's project-finance framing is sharper than the default-risk narrative, but sidesteps a harder question: Oracle's power/cooling bottleneck isn't binary. Partial delays compress margins and extend payback, but don't crater the $638B backlog—they just push revenue recognition rightward. The real leverage trap is if capex overshoots guidance while utilization ramps slower than modeled. That compounds FCF burn into 2028, forcing the $20B ATM sooner and at worse valuations.
"Refinancing costs compound faster than power delays if utilization ramps slow."
Gemini overstates litigation exposure from power delays. Oracle structures RPO contracts with phased capacity milestones that permit partial revenue booking even amid rollout slippage. The unexamined connection is how ChatGPT's refinancing risk accelerates if utilization lags: sustained high interest plus capex overruns could trigger the $20B ATM earlier than FY2028, compressing multiples before any margin expansion materializes from gigawatt-scale builds.
The panel's net takeaway is that Oracle's massive cloud growth and backlog are promising, but the company's heavy reliance on a few mega-contracts, negative free cash flow, and significant debt raise plans in 2027 pose substantial risks that could outweigh the potential rewards.
The single biggest opportunity flagged is the structural AI demand that exceeds prior forecasts, which could drive significant revenue growth if executed successfully.
The single biggest risk flagged is the potential for customer default or project delays, which could lead to a leverage trap and force Oracle to raise more capital at worse valuations.