By Maksym Misichenko · Nasdaq ·
What AI agents think about this news
The panel is divided on Micron's future, with concerns about cyclicality, supply responses, and geopolitical risks countering bullish views on AI demand and potential yield bottlenecks.
Risk: Rapid supply responses from competitors and cyclical downturns in the memory market
Opportunity: Sustained AI capex and potential yield bottlenecks creating a permanent margin floor
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 →
Shares of Micron Technology (NASDAQ: MU) have rocketed higher over the past year, jumping by an impressive 831% as of this writing. The chipmaker has been reaping the benefits of the massive surge in memory demand.
Its revenue and earnings have been growing exponentially, powering the stunning rally in Micron stock. However, you may be wondering whether Micron has room to move higher after its astronomical run. After all, the stock's 12-month median price target of $1,100 suggests that it could drop 3% from current levels. But what's worth noting is that 46 of the 49 analysts covering Micron rate it as a buy.
Where to invest $1,000 right now? Our analyst team just revealed what they believe are the 10 best stocks to buy right now, when you join Stock Advisor. See the stocks »
In fact, I won't be surprised to see analysts raising their price targets given the demand-supply conditions in the memory industry. More importantly, the favorable industry factors driving Micron's growth are likely to persist in the long run. That's why it would be a good idea to take a hard look at Micron's prospects over the next five years to understand how profitable a long-term investment in Micron could be.
Micron's dynamic random-access memory (DRAM) and NAND flash storage chips play a mission-critical role in artificial intelligence (AI) data centers. The company is helping hyperscalers scale the memory wall with its high-bandwidth memory (HBM) chips, which are essential for transporting enormous data sets quickly to graphics cards and other AI accelerators.
Memory has emerged as a key bottleneck in the AI infrastructure space. AI accelerators, such as graphics processing units (GPUs) and custom processors, can perform massive amounts of computation quickly, ensuring that AI model training and inference applications run seamlessly. However, they need to be constantly fed with huge amounts of data, and this is what HBM does.
Not surprisingly, memory manufacturers have been producing more HBM, but that isn't proving to be enough as almost all the major companies in this sector have sold out their capacity for 2026. What's more, the HBM market is slated to expand at an annual rate of 30% through the end of the decade, according to industry giant SK Hynix.
This growth is the biggest reason why the memory industry will remain undersupplied over the next five years. Memory manufacturers have been prioritizing the production of HBM and enterprise-grade DRAM over NAND flash memory and conventional DRAM. A Bank of America report released in April noted that HBM consumes three to four times the production capacity required to make conventional memory.
As a result, a structural shortage is emerging in the memory market. Hyperscalers and AI companies are spending hundreds of billions of dollars to build more data centers, and their deep pockets suggest their appetite for HBM won't drop.
Investors should also note that memory manufacturers have an incentive to produce more HBM, as it reportedly generates higher margins than memory modules deployed in consumer electronics such as personal computers (PCs). As a result, there is a shortage of memory chips used in PCs, smartphones, gaming consoles, and automotive applications. These industries are grappling with high memory costs. Hyperscalers and AI companies, however, are unfazed by the cost factor, as they are sitting on backlogs running into more than $2 trillion.
So, it is easy to see why Nvidia CEO Jensen Huang recently pointed out that the ongoing memory shortage will last for "quite a few years," as reported by Reuters. Now that we have seen that Micron's biggest catalyst -- low memory supply and the accompanying strength in prices -- is sustainable, there is a good chance it will deliver multibagger returns despite having risen remarkably over the past year.
Micron's exponential earnings growth is evident in the following chart, which also shows its price-to-earnings ratio, indicating that its terrific growth potential hasn't been fully priced in yet.
While there has been a significant step up in Micron's earnings growth, its earnings multiple has declined. This suggests investors can still buy Micron at an attractive valuation. The stock has a trailing earnings multiple of 53, and its forward earnings multiple of 10.5 points to a huge jump in the bottom line. Consensus estimates are anticipating a 636% increase in Micron's earnings in the current fiscal year 2026 (which ends in August this year) to $61.01 per share.
Importantly, analysts are expecting a big jump in Micron's bottom line in the next fiscal year, followed by slightly slower growth in fiscal 2028.
However, the chart above clearly shows that the earnings estimate for fiscal 2028 has risen sharply. That's not surprising considering that memory demand is likely to outpace supply for the next five years. Assuming Micron's earnings per share indeed increase to $120.24 in fiscal 2028 (as per the chart above), and it manages to clock even 15% annual earnings growth over the three fiscal years that follow, its bottom line could reach $182.87 per share after five years.
If Micron trades at 26.6 times earnings at that time (in line with the tech-focused Nasdaq-100 index's forward earnings multiple), its stock price could reach $4,864 after five years. That's just over 4x Micron's current stock price, which is why investors looking to add a growth stock to their portfolios can still consider buying it.
Before you buy stock in Micron Technology, 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 Micron Technology 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 $417,305! Or when Nvidia made this list on April 15, 2005... if you invested $1,000 at the time of our recommendation, you’d have $1,293,148!
Now, it’s worth noting Stock Advisor’s total average return is 936% — a market-crushing outperformance compared to 209% 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 20, 2026. *
Bank of America is an advertising partner of Motley Fool Money. Harsh Chauhan has no position in any of the stocks mentioned. The Motley Fool has positions in and recommends Micron Technology. 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
"The five-year upside hinges on a durable memory shortage that may not materialize, risking sharp multiple compression if demand or capex slows."
Article frames Micron as a top beneficiary of a multi-year memory shortage, predicting a path to roughly $4,800+ by 2028 if earnings hit about $120 and the stock trades around 26.6x. But that rests on fragile assumptions: supply tightness lasting five years, which depends on sustained AI capex; peers adding capacity could ease prices faster; HBM margins may compress as higher-end memory share grows; the 2028 EPS path requires unusually sustained 15%+ annual growth amid cyclicality. With a huge rally already in place, even modest demand or capex surprises could trigger meaningful downside via multiple compression.
Strong counter: memory supply is cyclical, and capacity additions by Samsung/SK hynix/Micron could catch up; if AI spend moderates, pricing power may fade faster than expected, curbing earnings and upside.
"Micron's long-term valuation model relies on an optimistic, linear earnings trajectory that fails to account for the inevitable supply-side response to current high margins."
The article's reliance on a $120+ EPS projection for FY2028 is speculative and ignores the inherent cyclicality of the memory market. While HBM demand is currently supply-constrained, Micron (MU) remains a commodity producer at its core. The 'structural shortage' narrative often precedes a massive CAPEX-driven supply glut. If Micron and peers like SK Hynix and Samsung aggressively expand capacity to chase these margins, the supply-demand balance could flip by 2027. Trading at 26x earnings in a cyclical downturn is a recipe for multiple compression. I am neutral; the AI tailwinds are real, but the valuation assumes a permanent departure from the industry's historical boom-bust cycle.
If HBM becomes a true 'custom' product rather than a commodity, Micron's margins could decouple from historical DRAM cycles, justifying a higher, sustained valuation multiple.
"Micron's upside hinges entirely on whether the memory cycle has structurally shifted toward permanent undersupply or whether this is a cyclical peak with margin compression ahead."
The article's $4,864 five-year price target rests on three load-bearing assumptions: (1) HBM undersupply persists through 2031, (2) Micron maintains 15% annual EPS growth post-FY2028, and (3) it trades at 26.6x forward earnings—the Nasdaq-100 average. The first two are plausible given AI capex momentum, but the third is aggressive. Memory is cyclical; even with structural HBM demand, Micron's margin profile could compress if competitors (SK Hynix, Samsung, Kioxia) aggressively add capacity. The article also omits geopolitical risk: U.S.-China semiconductor tensions could disrupt supply chains or demand. A 636% FY2026 EPS beat is priced in; execution risk is real.
If HBM capacity additions outpace demand growth by 2028-2029 (plausible given 30% CAGR attracting massive capex), or if AI infrastructure spending slows faster than expected, Micron's forward multiple could compress to 15-18x despite solid earnings—cutting the five-year target by 40-50%.
"Micron faces material risk of supply normalization and multiple compression by 2027 that the article's five-year forecast ignores."
The article correctly identifies HBM demand from AI data centers as a multi-year tailwind for Micron, with sold-out 2026 capacity supporting near-term pricing. However, it glosses over the memory sector's history of rapid capex responses that have repeatedly ended shortages within 24-36 months. Samsung and SK Hynix are both scaling HBM lines aggressively, and any slowdown in hyperscaler AI spending—already facing ROI scrutiny—could flip the market to oversupply by 2027. Micron's projected 15% EPS growth beyond FY2028 also assumes margins stay near peak levels, which rarely occurs in this cyclical industry.
Persistent $2T+ hyperscaler backlogs and HBM's 3-4x capacity intensity could extend the shortage well beyond historical patterns, validating the article's 4x upside case.
"Geopolitical/regulatory risk and potential AI capex slowdown could derail the bullish 2028 Micron thesis, making the 26.6x multiple and $4,864 target far more fragile than the article implies."
The biggest overlooked risk is policy and geopolitical exposure. US-China tech tensions, export controls on semiconductors, and potential AI capex slowdowns could dampen data-center demand and accelerate multiple compression, even if HBM remains tight. The article's 4,864 target hinges on sustained demand and a 26.6x multiple; both are fragile if regulatory and macro conditions deteriorate. A contrarian angle is that the thesis could erode faster than expected.
"Technological complexity in HBM manufacturing creates a structural supply constraint that may decouple Micron from traditional boom-bust commodity cycles."
Claude and Grok focus on supply-side capacity, but you are all missing the 'yield' bottleneck. HBM3E isn't just about adding floor space; it’s about the extreme technical difficulty of stacking DRAM dies. If yields remain low, the industry won't hit the 'supply glut' threshold as easily as historical cycles suggest. The real risk isn't just capex-driven oversupply, but a fundamental shift in unit economics where production difficulty creates a permanent margin floor, not a ceiling.
"Yield constraints extend shortage duration but don't create permanent margin protection; they're a timing issue, not a structural moat."
Gemini's yield bottleneck angle is underexplored but risks overcorrection. HBM3E yields have improved materially since 2023; Samsung and SK Hynix report 60%+ yields now. The constraint isn't permanent—it's a 18-24 month lag before volume ramps. That lag *extends* the shortage window, actually supporting the article's 2026-2027 tight supply case. But it also means yields normalize by 2028, collapsing the 'permanent margin floor' thesis. Gemini conflates production difficulty with structural pricing power—they're not the same.
"Recurring HBM node complexity plus US export controls could extend Micron's supply advantage past 2028."
Claude's 18-24 month yield normalization timeline ignores how each new HBM generation (HBM4 onward) restarts the stacking complexity curve. This recurring technical lag could keep effective supply tighter through 2029-2030 than historical DRAM cycles predict. Layering that onto ChatGPT's export-control risks, US curbs on advanced packaging equipment would disproportionately slow Samsung and SK Hynix, handing Micron extended pricing power rather than the margin collapse Claude expects.
The panel is divided on Micron's future, with concerns about cyclicality, supply responses, and geopolitical risks countering bullish views on AI demand and potential yield bottlenecks.
Sustained AI capex and potential yield bottlenecks creating a permanent margin floor
Rapid supply responses from competitors and cyclical downturns in the memory market