Bởi Maksym Misichenko · Nasdaq ·
Các tác nhân AI nghĩ gì về tin tức này
The panel generally agreed that the 'cheapest' Magnificent Seven stocks by forward P/E (NVDA, MSFT, META) are not necessarily undervalued, given the risks associated with their massive capex plans, potential margin compression from competition, and the fragility of forward multiples.
Rủi ro: The 'show me' phase where revenue growth must outpace ballooning depreciation costs, which could force P/E resets if AI monetization stalls.
Cơ hội: The 'Sovereign AI' shift, which creates a floor for NVDA’s demand due to government and domestic enterprises mandating localized data infrastructure.
Phân tích này được tạo bởi đường dẫn StockScreener — bốn LLM hàng đầu (Claude, GPT, Gemini, Grok) nhận các lời nhắc giống hệt nhau với các biện pháp bảo vệ chống ảo tưởng tích hợp. Đọc phương pháp →
These 3 stocks have excellent prospects, despite recent developments suggesting otherwise.
Buying their shares at current levels and holding onto them for the long haul could yield excellent returns.
The Magnificent Seven is a group of tech (or tech-adjacent) companies that are among the largest on the market. The list includes Alphabet (NASDAQ: GOOG) (NASDAQ: GOOGL), Amazon (NASDAQ: AMZN), Apple (NASDAQ: AAPL), Meta Platforms (NASDAQ: META), Microsoft (NASDAQ: MSFT), Nvidia (NASDAQ: NVDA), and Tesla (NASDAQ: TSLA). They are called "magnificent" partly because of their performance over the past decade or so: Every single one has outpaced broader equities. Some would argue that most of them still have plenty of upside left, but after the sustained runs we have seen from these leaders, others might worry that their future success is already baked into their share prices, leaving little room for market-beating returns.
For those with valuation concerns, it might be helpful to look at which ones among the Magnificent Seven are the most reasonably valued using common valuation metrics, such as the forward price-to-earnings (P/E) ratio, and go from there. Let's look into the three cheapest Magnificent Seven stocks based on this metric and decide whether it's worth investing in them.
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 »
It might be surprising to find Nvidia on this list. After all, it is the runaway, undisputed leader in the GPU (Graphics Processing Unit) market, the workhorse of artificial intelligence (AI) training. Few corporations have benefited from the AI boom as much as Nvidia over the past three years. Yet, the company's forward P/E of 23.8 makes it the second-cheapest Magnificent Seven stock right now.
GOOGL PE Ratio (Forward) data by YCharts
Should investors buy the stock? On the one hand, some will point to increased competition for Nvidia, including from Cerebras Systems, a recent IPO looking to challenge its dominance in the GPU market. Further, with the AI industry shifting from training to inference, there might be soaring demand for CPUs (Central Processing Units), a niche long dominated by other tech leaders, and one in which Nvidia will struggle to make a significant dent, at least that's what the detractors think.
Also, even Nvidia's recent outstanding financial results -- for the first quarter of its fiscal year 2027, ending on April 26 -- weren't able to jolt the stock. The company's revenue of $81.6 billion, which soared 85% year over year and beat internal projections and analyst estimates, evidently was not impressive enough. Even with all that, I still view Nvidia as a strong buy.
The AI tailwind is far from over, and Nvidia's high-performing GPUs and CUDA ecosystem make it incredibly hard to knock it off its pedestal. Meanwhile, it is making strides in the CPU market. It expects $20 billion in revenue for its stand-alone CPU business through the end of the year, and projects a $200 billion CPU addressable market thanks to the shift to agentic AI. Nvidia remains one of the best stocks to capitalize on the massive AI tailwind and is a buy at current levels.
Some investors think Microsoft will lose some business because AI will replace its services. Meanwhile, the company is expecting to spend small fortunes, to the tune of $190 billion during the calendar year 2026, on capex, largely to support its cloud computing and AI businesses.
The market remains unconvinced, though, and that's why Microsoft's shares have declined meaningfully over the past six months. Its current forward P/E of 24.5 makes it the third cheapest among the Magnificent Seven. At these levels, Microsoft also looks like a strong buy.
The company is evolving with the times and integrating AI across its services in ways that could make them more valuable -- not less -- to its customers. Also, Microsoft remains one of the leaders in cloud computing, and the company's expanding cloud backlog suggests sustained, and perhaps even accelerating, demand for its services. Lastly, the company benefits from a wide moat thanks to its brand name, switching costs, and the deep enterprise partnerships it has built over decades of offering its services.
It's not surprising to see Meta Platforms as the cheapest of the Magnificent Seven stocks, with a forward P/E of about 19.3. The tech leader's latest earnings update featured a sequential decline in daily active users and increased capex spending, which many fear won't pay off and will only squeeze margins and profits.
These are reasonable concerns, especially since the last time the market worried that Meta's heavy investments wouldn't pay off, it was right. The company's work on the metaverse didn't amount to much. However, Meta quickly cut expenses (before its more recent runaway capex spending) and shifted its focus to AI. That highlights an important fact: the company's vast ecosystem of over 3.56 billion users offers it umpteen monetization opportunities.
Meta's ecosystem is a significant advantage. AI has improved the company's advertising business through algorithms that have boosted engagement, while it has also launched AI-powered tools to enhance the ad launch process. Meta Platforms will continue relying on AI to grow its business and may ramp up opportunities beyond advertising over the medium term, such as paid and business messaging on WhatsApp. The stock is still a great pick for investors.
While the forward P/E ratio is helpful, it is only one of the many ways to determine whether a stock is overvalued. Investors should keep that in mind. Even with this caveat, though, Nvidia, Microsoft, and Meta Platforms have strong long-term prospects, given their innovative capabilities and competitive advantages.
Before you buy stock in Nvidia, 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 Nvidia 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 $465,733! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,313,467!
Now, it’s worth noting Stock Advisor’s total average return is 985% — a market-crushing outperformance compared to 211% 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 May 30, 2026. *
Prosper Junior Bakiny has positions in Alphabet, Amazon, Meta Platforms, and Nvidia. The Motley Fool has positions in and recommends Alphabet, Amazon, Apple, Meta Platforms, Microsoft, Nvidia, and Tesla. 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.
Bốn mô hình AI hàng đầu thảo luận bài viết này
"Forward P/E alone fails to account for capex intensity and competitive shifts that could pressure margins beyond 2026."
The article highlights forward P/Es of 23.8 for NVDA, 24.5 for MSFT, and 19.3 for META as attractive entry points, yet glosses over execution risks from the $190B MSFT capex plan in 2026 and META's sequential DAU decline amid rising AI spend. Nvidia's projected $20B CPU revenue faces Intel and AMD competition in inference workloads, while all three face potential multiple compression if AI ROI disappoints. Historical precedent shows Meta's prior heavy investments (metaverse) failed to justify spend before pivots. These metrics ignore balance-sheet strain and sector-wide valuation resets if growth slows below 20% EPS.
The strongest case against this caution is that CUDA lock-in and enterprise switching costs could sustain 30%+ revenue growth for NVDA and MSFT even if capex peaks, keeping current multiples justified.
"The article mistakes relative cheapness within an expensive peer group for absolute value, obscuring execution risk on massive capex bets and competitive threats that could compress margins materially."
This article conflates 'cheapest by forward P/E' with 'undervalued,' a dangerous leap. NVDA at 23.8x forward P/E isn't cheap—it's cheap *relative to the Mag 7*, a group trading at structural premiums. The article ignores that forward P/E assumes earnings materialize; for NVDA, that requires sustained AI capex cycles and no margin compression from competition (Cerebras, AMD, custom chips). META at 19.3x looks reasonable until you note sequential DAU declines and $190B capex commitments with unproven ROI. MSFT's $190B capex spend is real; the article hand-waves it. None of these are bargains in absolute terms—they're relatively less expensive within an expensive cohort.
If AI capex cycles accelerate and these companies' moats hold (CUDA, Azure lock-in, Meta's 3.5B user network), forward earnings could grow 25%+ annually, making 23–24x P/E ratios justified and these stocks genuinely cheap on a 3–5 year view.
"Forward P/E metrics are currently misleading because they fail to account for the massive, unproven capex drag on future free cash flow."
The article's reliance on forward P/E as a primary valuation metric for the Magnificent Seven is dangerously reductionist. While a forward P/E of 19-24x looks cheap compared to historical tech multiples, it ignores the massive, non-linear capital expenditure (capex) cycles these firms are entering. For Microsoft and Meta, the 'cheapness' is a reflection of market skepticism regarding the ROI on $100B+ AI infrastructure spends. If these investments fail to drive immediate margin expansion, the P/E compression is justified rather than an opportunity. Investors are currently pricing in a 'show me' phase where revenue growth must outpace ballooning depreciation costs, making these stocks 'value traps' if AI monetization stalls.
If these firms possess genuine 'indispensable monopoly' status, the current P/E multiples are actually buying opportunities before the next wave of AI-driven operating leverage kicks in.
"Forward P/E alone is an insufficient, risk-adjusted signal; AI cycle durability and macro conditions could drive multiple contractions even for the cheapest names."
By spotlighting forward P/E, the piece labels Nvidia, Microsoft, and Meta as the three 'cheapest' Magnificent Seven—a tempting contrarian cue. But forward multiples are fragile; they ride consensus earnings and an AI cycle that could surprise to the downside if demand cools or capex overruns. Even at those multiples, NVDA’s growth-tilted earnings, MSFT’s massive cloud spend, and Meta’s ad-revenue risk may compress margins if AI spend slows or regulatory headwinds bite. The article glosses over cash-flow quality, balance-sheet strength, and non-earnings drivers (pricing power, subscriptions) and ignores other valuation metrics (EV/FCF, P/S). Bottom line: cheap by one metric is not enough.
Yes, AI tailwinds could persist longer than feared, and a re-rating could occur if earnings prove durable; the so-called 'cheap' names may actually surprise to the upside.
"Hyperscaler custom silicon could accelerate margin pressure on NVDA ahead of broader competition."
Claude notes NVDA's 23.8x forward P/E assumes earnings materialize but underplays how hyperscaler custom chips could compress NVDA margins before AMD or Cerebras scale. This timing risk connects directly to Gemini's depreciation warning: if MSFT and META's combined $190B+ 2026 capex drives faster opex growth than AI revenue, the 'show me' phase forces P/E resets across the group regardless of CUDA lock-in.
"Forward P/E ignores the timing mismatch between capex depreciation hitting income statements now and AI revenue upside arriving later."
Grok conflates two separate risks: custom chips eroding NVDA margins (real, 2–3 year horizon) versus capex-driven opex outpacing revenue (immediate, 2025–2026). The second is the actual trap. MSFT and META could see *absolute* FCF compression even if revenue grows 15%+ if depreciation accelerates faster than operating leverage materializes. That's the 'show me' phase Gemini flagged—and it's not priced into forward P/E at all.
"Geopolitical mandates for sovereign AI infrastructure provide a non-commercial demand floor that mitigates the risks of traditional capex-to-ROI analysis."
Claude and Gemini are fixated on depreciation, but you're all ignoring the 'Sovereign AI' shift. Governments and domestic enterprises are now mandating localized data infrastructure, which forces capex spend regardless of immediate ROI. This isn't just corporate vanity; it is a geopolitical necessity that creates a floor for NVDA’s demand that custom silicon cannot replicate. The 'show me' phase is irrelevant if the customer base is forced to buy for national security, not just efficiency.
"Sovereign AI demand is not a reliable moat; treat it as a tailwind, not a guaranteed backstop."
Gemini overstates the 'sovereign AI' floor. Government-driven capex can buoy demand, but procurement is lumpy, cyclical, and often renegotiated; localization pushes costs up and may squeeze ROI if offsets aren’t matched by revenue. Relying on sovereign buys as a durable moat risks air-pocket timing and regime changes. NVDA/MSFT/META still face 2025–26 depreciation/opex headwinds; sovereign demand is a tailwind, not a guaranteed backstop.
The panel generally agreed that the 'cheapest' Magnificent Seven stocks by forward P/E (NVDA, MSFT, META) are not necessarily undervalued, given the risks associated with their massive capex plans, potential margin compression from competition, and the fragility of forward multiples.
The 'Sovereign AI' shift, which creates a floor for NVDA’s demand due to government and domestic enterprises mandating localized data infrastructure.
The 'show me' phase where revenue growth must outpace ballooning depreciation costs, which could force P/E resets if AI monetization stalls.