double_m
2 days ago
AppLovin Stock Takes a Hit After Muddy Waters’ Short Call
March 27, 2025
Ari Haruni
AppLovin’s (APP) stock dropped nearly 12% to $290 on Thursday after Muddy Waters’ report estimated that 52% of its e-commerce sales are from retargeting, with only 25%-35% being new business, questioning its growth value.
The report claims AppLovin violates platform rules by collecting user IDs, risking deplatforming like Cheetah Mobile, or facing copycat competitors if it survives, threatening its market position.
With a 23% client loss in Q1, Muddy Waters suggests advertisers are noticing weak results, putting pressure on AppLovin’s plans as its stock reflects growing investor unease.
AppLovin Corp. (APP), a company running a mobile marketing platform, saw its stock plummet nearly 12% to $291 during Thursday trading, rattled by a report from Muddy Waters, a research firm betting against it. The firm’s digging into web traffic suggests that about 52% of AppLovin’s e-commerce sales come from retargeting – reaching out to people who’ve already shown interest – but only 25% to 35% of those sales are actually new business, not just repeat customers. This gap raises doubts about how much real growth AppLovin is driving, a concern that could spook the advertisers it relies on to keep the engine running.
Muddy Waters didn’t stop there. They claim to have found code showing AppLovin is grabbing and organizing user IDs from big platforms it works with, a move they say breaks those platforms’ rules. If they’re right, AppLovin could get kicked off those services, much like what happened to Cheetah Mobile years back when it got caught in similar hot water. But even if AppLovin dodges that bullet, the report warns that competitors might just copy its playbook since there’s not much unique tech keeping it ahead—just bold tactics. That could flood the market with rivals doing the same thing, squeezing AppLovin’s edge.
The numbers aren’t looking great elsewhere either. Muddy Waters spotted a 23% dropout rate among AppLovin’s e-commerce clients in Q1, hinting that businesses might be catching on that the platform’s not delivering the bang for their buck they’d hoped for. With shares sliding 12%, the market’s clearly jittery about whether AppLovin can keep its growth story alive. Advertisers want results, not just recycled customers, and if Muddy Waters is on the mark, AppLovin’s got a tough road ahead to prove it’s more than a one-trick pony in a crowded, cutthroat field.
https://wallstreetpit.com/125561-applovin-stock-takes-a-hit-after-muddy-waters-short-call/
Whalatane
2 days ago
AppLovin keeps Outperform rating at Oppenheimer after Shoptalk 2025 event
Oppenheimer maintained its Outperform rating on AppLovin (NASDAQ:APP) while highlighting key points for the company from the annual retail and e-commerce industry conference, Shoptalk 2025.
The firm has a $560 price target on AppLovin, which provides a software platform for advertisers.
Analysts led by Martin Yang said they attended Shoptalk 2025 and spoke to agencies, brands, and measurement partners that work with AppLovin on e-commerce marketing. They said the overall commentary regarding the company's performance, product features, and customer relationship remains positive.
Most incrementally, the analysts added that they learned that AppLovin's self-serve portal is being released this month to a limited group of customers.
Regarding the first quarter 2025 trends, one measurement partner noted that AppLovin's share of wallet is increasing quickly from the fourth quarter of 2024 to the first quarter of 2025, the analysts added.
At a presentation by AppLovin and marketing measure platform Fospha noted that its 10 brand customers are consistently spending more on
AppLovin. January 2025 spending is 2% higher than December 2024, and February 2025 spending is 25% higher than January 2025, with no sign of slowing, according to the analysts. ( my emphasis )
Yang and his team said that customer and measurement partners' commentary continues to support their bullish view on AppLovin's ecommerce growth.
Kiwi
Whalatane
6 days ago
From Grok AI
AppLovin holds a significant position in Flip Shop as a strategic investor and technology partner.
In April 2024, AppLovin invested $50 million in Flip's $144 million Series C funding round, contributing to Flip's pre-money valuation of $1.05 billion.
Beyond financial investment, AppLovin has partnered with Flip to enhance its advertising capabilities by integrating AppLovin’s AXON technology into Flip’s platform.
AXON, an AI-powered advertising engine launched by AppLovin in early 2023, allows Flip brands to leverage advanced ad targeting and reach more customers, including access to AppLovin’s network of 1.4 billion daily active users (DAUs).
This collaboration positions AppLovin as a key enabler of Flip’s marketing platform, aiming to boost sales and user engagement for brands on Flip while expanding AppLovin’s influence in the social commerce space.
As of now, TikTok remains operational in the U.S., but its fate hinges on whether ByteDance divests by April 5, 2025, or if further legal or political actions alter the situation.
The Supreme Court upheld the divest-or-ban law on January 17, 2025, rejecting TikTok's First Ame
ndment challenge, so without a sale or additional intervention, TikTok would be required to shut down after April 5, 2025, unless the deadline is extended again or the law is repealed.
The situation remains fluid, with ongoing negotiations and political maneuvers potentially affecting the outcome.
And the short term effect on Flip Shop
Flip, a “shopping social network” featuring video reviews from creators and shoppers, saw a massive surge in interest as TikTok users sought alternatives.
Data from Linktree, reported on February 7, 2025, showed a 400-570x increase in links to alternative apps like Flip during the week leading up to and including the shutdown.
Specifically, Flip experienced a 25x increase in new user installs month-over-month on January 18 alone, with 250,000 new sign-ups since early January 2025, according to Modern Retail.
This propelled Flip to the top of Apple’s App Store rankings, reflecting a flood of TikTok users migrating to the platform.
Kiwi
Whalatane
2 weeks ago
I'll probably wait for a retest of the recent low , before possibly adding any . Ideally I like to buy fear / vomits if I believe in , or are willingly to speculate in , the underlying fundamentals .
APP has shown explosive earnings growth late 2024 ....will it continue ?
We know that the Dec rev run rate annualized at $1b ....but we won't know full details of Q1 until around May 7th
Meanwhile
Trends and Insights
Earnings Growth: AppLovin’s earnings growth has accelerated sharply, with a 363.4% year-over-year increase in 2024, far outpacing its five-year compound annual growth rate of 67%. This reflects operational efficiency gains and a strategic pivot away from its apps business (planned divestiture in Q2 2025) toward its advertising platform, particularly the AI-powered AXON technology.
Revenue Consistency: Revenue has grown consistently since 2020, with a notable jump in 2024, driven by a 66% increase in software revenue in Q3 2024 alone, highlighting the success of its advertising focus.
Profitability Shift: The transition from a net loss in 2022 to substantial profits in 2023 and 2024 underscores improved margins (e.g., 62% adjusted EBITDA margin in Q4 2024) and cost management, with free cash flow rising 105% year-over-year to $695 million in Q4 2024.
AppLovin’s historical earnings trends show a company moving from modest revenue growth and profitability struggles to explosive earnings and revenue gains, particularly in 2024, as it capitalizes on digital advertising demand.
So does the explosive growth continue ?...or does weakness in the economy also drag down their revenues ?
Test the recent lows and I might add ...otherwise will just sit with what I have until the Q1 earnings report
Good luck
Kiwi
rosemountbomber
2 weeks ago
Kiwi, thanks for the Axon primer. The question comes up as to whether it has made much penetration beyond gaming and into e-commerce. An article today sounds a bit negative in those regards and might be of interest."
The analyst examined over 2,200 ecommerce websites for the Axon pixel, which indicates a partnership with APP for advertising. The pixel tracks user interactions from ads to websites. The analyst found 297 websites with the pixel, aligning with APP’s reported 600 advertisers by the end of 2024. The websites were categorized by product type and are also monitoring 60 major brands that could become significant advertisers on the platform.
APP is working with a diverse range of product categories, with over 40% of the websites in the Health & Personal Care sector, a significant category in U.S. retail ecommerce.
Apparel, footwear, and accessories make up 25% of the websites tracked. This broad category representation underscores the potential for large advertising spend and highlights the vast market opportunity for APP's new venture. While most of the 2,200 websites in the survey are smaller DTC products, 60 major brands like Nike, Amazon, and Etsy are key to tracking, as they could significantly boost advertising revenue for APP. From this list, only Wayfair was found to have the APP pixel installed, noted the analyst.
According to the analyst, AppLovin is poised to benefit from the growing shift toward in-app advertising (IAA) and the increasing importance of first-party consumer data.
Whalatane
2 weeks ago
Explain AXON technology
AXON is AppLovin’s AI-based advertising technology, designed to optimize and scale digital marketing campaigns with a focus on precision and efficiency. Launched in early 2023, it’s a core component of AppLovin’s marketing platform, which originally grew out of mobile gaming but has since expanded into broader app and e-commerce ecosystems, including its partnership with Flip. Here’s a breakdown of what AXON is, how it works, and why it matters as of March 16, 2025.
What It Is
AXON stands for "Advertising eXchange Optimization Network" (though AppLovin doesn’t always spell out the acronym). It’s an advanced machine learning system that powers ad delivery by analyzing vast amounts of data to predict user behavior, match ads to the right audiences, and maximize return on ad spend (ROAS). Think of it as the brain behind AppLovin’s ability to connect advertisers—whether game developers, app makers, or e-commerce brands—with their ideal customers across a network of over 1.4 billion daily active users.
How It Works
AXON operates on a few key principles:
Data-Driven Targeting: It ingests real-time data from user interactions—like app usage, clicks, purchases, and even contextual signals (e.g., time of day, device type)—across AppLovin’s network of apps and partner platforms. This data pool is massive, leveraging AppLovin’s scale from its gaming origins and its acquisition of MoPub in 2021, which broadened its reach.
Predictive Modeling: Using deep learning algorithms, AXON predicts which users are most likely to engage with a specific ad. It doesn’t just look at past behavior but anticipates future actions, such as whether a user will install an app, make a purchase, or scroll past. This predictive power comes from training on billions of data points, refined continuously as more interactions occur.
Dynamic Optimization: Once it identifies high-value users, AXON dynamically adjusts ad placements, formats (e.g., video, banner, native), and bidding strategies in real time. It balances cost-per-action (CPA) goals with scale, ensuring advertisers get the most bang for their buck without overspending.
Creative Enhancement: AXON also optimizes ad creatives themselves. It can test variations—like tweaking colors, text, or video length—and prioritize the ones that perform best, all without manual input from advertisers.
The result? Ads that feel less random and more relevant, delivered at the right moment to the right person, often with higher conversion rates than traditional ad tech.
Why It Matters
AXON’s edge lies in its efficiency and scale. For advertisers, it promises better performance—AppLovin claims it can double ROAS compared to non-AI solutions—while reducing the guesswork of campaign management. In Flip’s case, for example, AXON powers the relaunched Flip marketing platform (via AXON Connect), helping brands reach Flip’s 5 million+ users and AppLovin’s broader network with ads that drive sales. This is critical in social commerce, where engagement and trust (e.g., through authentic reviews) need to translate into purchases quickly.
From a technical standpoint, AXON builds on AppLovin’s history of innovation. It evolved from their earlier tools like AppDiscovery, but with a heavier reliance on AI post-2023, reflecting trends in ad tech where machine learning is replacing rule-based systems. Competitors like Google’s Performance Max or Meta’s Advantage+ use similar AI-driven approaches, but AXON benefits from AppLovin’s tight integration with mobile ecosystems and its focus on performance marketing over brand awareness.
Real-World Impact
In practice, AXON has been a game-changer for AppLovin’s growth. By Q3 2024, the company reported a 39% year-over-year revenue increase to $1.2 billion, with AXON cited as a key driver. For Flip, the tech underpins its ability to scale ad revenue and user acquisition, supporting its $1.4 billion post-money valuation after the 2024 Series C round. Critics, however, argue that AXON’s reliance on incentivized user actions (e.g., Flip’s coupon-for-ad model) might inflate short-term metrics at the expense of long-term loyalty, a debate still playing out in financial circles.
In Simple Terms
Imagine AXON as a super-smart matchmaker. It takes a flood of data about what people do online, figures out who’s likely to buy what, and then serves up the perfect ad at the perfect time—all in milliseconds. It’s less about blasting ads everywhere and more about hitting the bullseye with minimal waste. For companies like Flip, it’s the engine that turns scrolling into shopping, backed by AppLovin’s AI muscle.
That’s AXON: high-tech, high-stakes, and a big reason AppLovin’s playing in the e-commerce big leagues alongside its gaming roots.--
--------------
Kiwi
Whalatane
2 weeks ago
A Grok ( AI ) look at APP's e-commerce entry
Let’s dive into the technical details of how AppLovin’s Axon technology powers its e-commerce advertising push as of March 15, 2025. While AppLovin keeps the inner workings of Axon proprietary—often calling it a "black box"—we can piece together a detailed picture based on its functionality, public statements, and industry context. Here’s a breakdown of the tech specifics tailored to its e-commerce application.
Core Technology: Axon’s AI Engine
Axon is a machine learning-driven recommendation engine that processes vast datasets to predict user behavior and optimize ad delivery. In e-commerce, it shifts from its gaming roots (predicting app installs) to forecasting purchase intent. The system ingests trillions of daily in-app events from AppLovin’s network—over 1.4 billion daily active users across 140,000+ apps—covering actions like clicks, views, and conversions.
For e-commerce, this expands to include first-party data from the AXON Pixel, a tracking tool brands embed on their sites or apps. This pixel captures granular signals: product views, cart additions, checkout initiations, and purchases.
The AI uses predictive modeling, likely a mix of supervised and unsupervised learning, to identify patterns. Think logistic regression or neural networks trained on historical data to classify users by intent—e.g., “high likelihood to buy” vs. “just browsing.” Unlike demographic-heavy approaches, Axon leans on behavioral data, analyzing real-time interactions rather than static traits. It’s processing at microsecond speeds, handling thousands of bid decisions per second in real-time auctions via AppLovin’s MAX platform.
Data Pipeline and Infrastructure
The backbone is an elastic cloud infrastructure, probably AWS or Google Cloud, optimized for scale. AppLovin’s App Graph—a data layer aggregating anonymized interactions—feeds Axon. In e-commerce, this pipeline integrates AXON Pixel data with network-wide signals, creating a unified dataset. Imagine a distributed system with tools like Apache Kafka for streaming data and Spark for processing, though specifics aren’t public. The system’s scale is hinted at by its ability to handle 10 terabytes daily (per older 2021 stats), likely much higher now with e-commerce added.
Data is cleaned, normalized, and fed into Axon’s models, which continuously retrain—possibly using online learning techniques like stochastic gradient descent—to adapt to shifting trends (e.g., holiday shopping spikes). This adaptability is key for e-commerce, where seasonality and product cycles demand agility.
Targeting and Ad Delivery
In e-commerce, Axon targets users across AppLovin’s mobile app inventory—games, utility apps, etc.—rather than just web browsers. It uses contextual and behavioral signals to decide who sees an ad. For instance, if a user adds sneakers to a cart on a DTC site, the AXON Pixel logs this, and Axon matches it to similar behaviors in its network (e.g., frequent in-app shoppers). The AI then bids via MAX’s in-app bidding tech, a real-time auction system that competes with other ad networks for impressions.
Bids are calculated using expected value models—multiplying predicted conversion probability by the advertiser’s payout (e.g., cost-per-sale). The system optimizes for ROAS (return on ad spend), adjusting bids dynamically based on performance. Ads are delivered as dynamic product ads (DPAs), pulling from product feeds to show specific items—like those sneakers—tailored to the user. Formats include full-screen interstitials, playable ads, or video, all rendered in-app for higher engagement than traditional banners.
Creative Optimization
AppLovin’s SparkLabs studio uses generative AI to craft these ads. The tech likely involves variational autoencoders or GANs (generative adversarial networks) to iterate on creatives—testing thousands of variations (e.g., colors, CTAs) against performance data. Axon feeds back which versions drive clicks or sales, refining the output. In e-commerce, this means ads aren’t static; they evolve to match user preferences, like showing a discount code to a price-sensitive shopper. This closed-loop system—targeting plus creative—boosts conversion rates, with AppLovin claiming “nearly 100% incrementality” in early pilots.
E-Commerce-Specific Enhancements
The Axon 2.0 upgrade (2023) improved scalability and efficiency, critical for e-commerce’s broader scope. It likely expanded model capacity—think deeper neural nets or ensemble methods—to handle diverse verticals beyond gaming. A big addition is AXON Connect, debuted with Flip in 2024, letting third-party platforms (like Flip’s marketplace) tap Axon’s engine. This involves an API layer where external data (e.g., Flip’s user activity) integrates with AppLovin’s, extending reach while keeping the core AI centralized.
For e-commerce, Axon also leverages connected TV (CTV) supply, though mobile remains dominant. Ads here might use similar behavioral targeting, but the tech adapts to CTV’s impression-based pricing vs. mobile’s cost-per-install focus. The system’s agnostic design—built on predictive ML—lets it flex across channels.
Challenges and Black-Box Limits
The tech isn’t flawless. Its opacity frustrates some advertisers who can’t peek under the hood—akin to Google’s Performance Max. Data privacy is another hurdle; while AppLovin avoids IDFA reliance (post-Apple’s 2021 changes), it still navigates app permissions and regional regs like GDPR. Short-seller claims in February 2025 alleged shady data practices (e.g., exploiting permissions), but no proof has stuck—still, it highlights risks in scaling such a data-hungry system.
Performance Metrics
By Q3 2024, e-commerce contributed to a 66% software revenue jump ($835M), with Q4 hitting nearly $1B (73% growth). The tech’s efficiency shows in margins—73% in Q4 2023—driven by automation reducing human overhead. Early e-commerce tests with DTC brands and Flip suggest Axon’s precision outstrips rivals, though exact conversion rates remain undisclosed.
In essence, Axon in e-commerce is a high-speed, AI-orchestrated machine: it ingests behavioral data, predicts intent, bids smartly, and serves evolving ads—all at scale. It’s less about reinventing the wheel and more about turbocharging it for a new road. Want me to drill deeper into any piece—like the ML models or bidding logic?
..............................
APP's Axon -2 upgrade is an automated version of what my oldest son does for an Ad tech company...designing and manually manipulating ads via META
Right now I think Axon -2 is limited to those spending $600k a month ....but as they fine tune it , it'll become more available
Kiwi
Whalatane
3 weeks ago
Well disappointing they weren't added in the S&P rebalancing .
Thoughts from Grok
, short-seller reports from firms like Fuzzy Panda Research and Culper Research, which emerged in early 2025 (though after the December decision), alleged fraudulent practices in AppLovin’s ad-tech business, particularly its AXON software. While these reports likely did not directly influence the December 2024 rebalancing, they reflect pre-existing skepticism about AppLovin’s business model that may have been shared by the committee. Fuzzy Panda later urged the committee in a March 4, 2025, letter to exclude AppLovin from the next rebalancing (expected March 2025), citing these concerns.
If similar doubts were present earlier, they could have impacted the committee’s view of AppLovin’s long-term stability, a key consideration beyond raw financial metrics.
Another possibility is that the committee saw AppLovin’s valuation as overstretched—trading at 104 times earnings in late 2024—potentially signaling risk despite its growth. In contrast, Workday, added in December, had a lower market cap but a more established track record in cloud software, possibly aligning better with the index’s “gold standard” as described by critics like Fuzzy Panda.
Ultimately, the S&P 500 rebalancing decisions are discretionary and opaque, balancing objective criteria with subjective judgment. AppLovin’s exclusion likely stemmed from a combination of these factors—sector representation, perceived risk, or timing—rather than a single definitive reason.
So they may need to deploy that funded share buyback program next week . Q1 earning report at least 6 wks away .
Their advertising rev exploded in Q4 ...but recent signs of consumer pull back may pressure that this Qt.
I'm not trading it unless theres a crash to near $200..... where I may buy some more .
I'll wait for Q1 earnings before I sell any
JMO
Kiwi
Register for Free to get streaming real-time quotes, interactive charts, live options flow, and more.
JohnQQ
1 day ago
Hot Features
Premium
