[HN Gopher] Launch HN: Shaped (YC W22) - AI-Powered Recommendati...
___________________________________________________________________
Launch HN: Shaped (YC W22) - AI-Powered Recommendations and Search
Hey HN! Tullie and Dan here from Shaped (https://www.shaped.ai/).
We're building a semantic recommendation and search platform for
marketplaces and content companies. There's a sandbox at
https://play.shaped.ai/dashboard/home that you can use to explore
demo models and evaluate results interactively. And we have a demo
video at https://www.youtube.com/watch?v=toCsUYQnJ_g. The
explosion of online content, driven by both individuals and
generative tools, is making it harder than ever for users to sift
through the noise and find what's relevant to them. Platforms like
Netflix, TikTok, and Meta have set a high bar, proving that
personalized experiences are key to cutting through the clutter and
engaging users effectively. Despite advancements in AI and
semantic infrastructure like vector stores, building a truly
relevant recommendation or search system is still extremely
difficult. It's not just about deploying the latest LLM--the
difficulties lie in creating the infrastructure to orchestrate the
components seamlessly. Consider the challenge of continuously fine-
tuning models with fresh data while simultaneously serving real-
time personalized recommendations to millions of users. It requires
a delicate balancing act of speed, scale, and sophistication. Our
goal is to empower any technical team to build state-of-the-art
recommendation and search systems, regardless of their data
infrastructure. Here's how we eliminate the friction: Solving Data
Challenges: We integrate directly with your data sources--Segment,
Amplitude, Rudderstack, and more. We handle the complexities of
real-time streaming, ETLs, and data quality robustness, so you can
get started in minutes. Leveraging Cutting-Edge Models - we
utilize state-of-the-art large-scale language, image, and tabular
encoding models. This not only extracts maximum value from your
data but also simplifies the process, even with unstructured data.
Real-time Optimization: Unlike vision or NLP tasks, recommendation
system performance hinges on real-time capabilities--training,
feature engineering, and serving. We've architected our platform
with this at its core. We're already helping many companies build
relevant recommendations and search for their users. Outdoorsy, for
example, uses us to power its RV rental marketplace. E-commerce
businesses like DribbleUp and startups like Overlap have seen up to
a 40% increase in both conversions and engagement when integrating
Shaped. A bit about us: Tullie was previously an AI Researcher at
FAIR working on multimodal ranking at Meta. He released
PyTorchVideo, a widely-used video understanding library, which
contains the video understanding models that power systems like IG
Reels. Dan led product research at Afterpay and Uber, driven by how
behavioral psychology influences user experience. We've been heads
down building Shaped for quite a while, so this launch feels like a
big milestone. We'd love to hear your feedback - technical deep
dives, feature requests, you name it. Let us know what you think!
Author : tullie
Score : 93 points
Date : 2024-08-13 14:19 UTC (8 hours ago)
| philip1209 wrote:
| How do you measure quality? And, can users game that quality?
|
| I think that's the hardest thing on any recommendation or search
| system. It's really hard to do without using money as a neutral
| measure of value. And, without a good measure of quality - it's
| unclear that the system is optimizing the right metrics (without
| cannibalizing others).
| tullie wrote:
| Thanks for the first question!
|
| We run online A/B tests to objectively measure quality against
| our ranking algorithms and other baselines. As you mentioned
| it's crucial that the measure of quality for these tests chosen
| is fair and correlates with the topline business objective.
| E.g. if you just evaluate clicks then the system will show
| click-baity content and overall perform worse.
|
| To handle this, we make it really easy to define different
| objectives and experiment with how it changes results. So
| although we don't claim to solve the issue directly, we believe
| that if users can quickly experiment with different proxy
| objectives, that'll be able to find the one that correlates
| with their topline objective quicker.
| candiddevmike wrote:
| This seems like a tough build vs buy sell. For a lot (most?)
| companies, the search/recommendation system isn't necessarily
| optimized for the customer's search. Instead, it's a way to
| maximize revenue via preferred placement or inject ads. This
| almost always leads to a gigantic if/else chain of bespoke
| business analyst driven decisions for the marketplace.
|
| How are you going to allow folks to influence the system? Or do
| you see your system integrated behind their pseudo-recommendation
| engine?
| authorfly wrote:
| Can you tell me what industry your viewpoint is from? My
| viewpoint from another industry is also about maximizing
| revenue - but if/else statements have no part, it's data-
| derived.
| tullie wrote:
| The build vs buy decision does come up, but like you mentioned,
| the product direction of Shaped is to be primitives for search
| and recommendation, allowing users that want to build use
| Shaped to empower them to build quicker (e.g. integrated behind
| their psudo-recommendation engine). In truth we have multiple
| abstractions to Shaped allowing more technical teams to
| integrate like this, or less technical ones to have more of an
| end-to-end integration experience.
|
| The other related market trend we think about here:
| recommendation is going through a similar journey to what
| search did 10 years ago. Search at some point was more build
| leaning, but over time the technology became democratized and
| then companies like Elastic and Algolia had offerings that
| pushed search to lean towards buy. We're seeing recommendations
| going through the same revolution now that the technologies and
| system design (e.g. 4 stage recommenders) are more solidified.
| It's the data that makes these systems unique between companies
| not the infrastructure or algorithms.
| esafak wrote:
| A company doing that doesn't understand LTV.
| sidcool wrote:
| What are the underlying ML models? Open source or custom trained?
| tullie wrote:
| We have a library with about 100 algorithms which you can
| choose from or by default we automatically choose based on your
| objective.
|
| Majority of them are open source models we've forked and
| improved. Just as an example, we integrated in gSASRec last
| week: https://github.com/asash/gSASRec-pytorch, and added a
| couple of improvements on scale and the ability use language
| and image features. We use LLMs for the encoding of
| unstructured data, and we host these our self, although OpenAI
| and Gemini are used for error message parsing and intelligent
| type inference, things not on the real-time path.
|
| More info here: https://docs.shaped.ai/docs/overview/model-
| library
| AnujNayyar wrote:
| Congratulations on the launch. We've weighed up algolia, in
| house, type-sense etc and so I'd would have been very keen to
| know more, but asking for us to integrate before knowing the
| pricing is a tough sell.
|
| Would highly recommend having at least an estimated pricing
| calculator so we can determine if its worth our time to install.
| tullie wrote:
| Thank you!
|
| Would love to chat, we've had several customers come over from
| Algolia and they've seen significant uplift. I can share more
| if you want to message me at tullie@shaped.ai.
|
| Our pricing is competitive with Algolia's to give you an idea
| there. We really wanted to get pricing calculator done get
| before this post but ran out of time. Keep an eye out over the
| next month for it to come up!
| hajrice wrote:
| How does it compare to Algolia?
| tullie wrote:
| The short answer is: we're better at recommendations and
| personalization and lean towards more technical teams (e.g.
| even with data/ML experience). They're better at traditional
| search and, these days, lean towards less technical teams.
|
| Longer answer is in our blog post about it:
| https://www.shaped.ai/blog/shaped-vs-algolia-recommend :)
| hajrice wrote:
| Cool! Any live demos we can try?
| tullie wrote:
| Yes play.shaped.ai! We just opened that up in a gateless
| way for this post. Let me know what you think. I should
| also mention that these demo models are on our cold-tier so
| that it doesn't break things, in production there's a big
| speed up.
| astronautas wrote:
| How does this compare to Vespa? If the key difficulty in scaling
| search is infra as you say, Vespa is an interesting alternative.
| tullie wrote:
| Compared to Vespa, we're much easier to get setup on. A big
| part of this is that we have real-time and batch connectors to
| all leading CDPs and data warehouses. E.g. if you're on
| Amplitude it takes < 10mins to stream data directly to Shaped
| and start seeing initial results.
|
| Being quicker to setup, also means it's quicker to build and
| experiment with new use-cases. So you can start with a feed
| ranking use-case the first week and then move to an email
| recommendation use-case the next week.
|
| In terms of actual performance and results, we've never gone
| head-to-head in an A/B test so i'm not sure the specifics there
| honestly!
| gk1 wrote:
| Congrats (from Pinecone) on the launch! The e-commerce and media
| recommendation space desperately needs an AI-based solution
| without the lead-filled baggage of legacy search or recommender
| systems.
|
| > 100M+ Users I assume you mean 100M+ end-users have interacted
| with a site or product that uses your technology. The way it's
| phrased sounds like you're saying Shaped itself has 100M+ users
| which of course it doesn't. Consider replacing that with "100M+
| interactions" or something.
| tullie wrote:
| Thank you! Would love to catch up sometime assuming you're in
| NYC with the rest of the Pinecone team!
|
| Yes by 100M+ users we definitely mean end-users, wasn't
| intentional to mislead so thanks for flagging -- we'll update.
| deepskyai wrote:
| Congrats Dan and Tullie - and the rest of the team. Great to see
| AUSTRALIA and particularly Melbourne (formerly known as the most
| liveable city in the world) represented. Is there anything
| different now compared to what you released ~18 months ago? Or
| just launching on HN now?
| tullie wrote:
| Australia represent! Although we're based in NYC we still are a
| mostly Aus/international team over here, it's great!
|
| The biggest change is some of the less sexy stuff, like scale
| and security. E.g. we're now able to scale to 100M+ MAU
| companies with 100M+ items, and we have a completely tenant
| isolated architecture, with security as a top priority.
|
| We've also made the platform more configurable and lower levels
| and we've found that people like choosing their own models and
| experimenting rather than just relying on our system.
|
| Finally, we launched search only a couple of months ago and are
| currently heavily focused on building a best-in-class
| experience there.
| jvans wrote:
| How do you personalize to the specific signals of the product, do
| they ingest into your infrastructure? What happens if a customer
| discovers a bug in a feature they're ingesting, how do they have
| control of retrains/pinning model versions? Who handles
| monitoring, the customer or your service?
| tullie wrote:
| Yes when integrating Shaped you connect up the data sources
| needed to ingest: interactions, items and users. The Shaped
| interface then allows you to select which exact fields should
| be used for creating a Shaped model. We provide a full SQL
| interface to do this, which gives a lot of flexibility.
|
| Our dashboard provides monitoring to help understand what data
| is ingested and view data quality over time. We expect
| customers to monitor this but also have alerts on our side and
| jump in to help customers if we see anything unexpected.
|
| The dashboard also shows training metrics over time (how well
| does the model predict the test set after each retrain?) and
| online attribution metrics (how well does the model optimize
| the chosen objective?).
|
| Customers can disable retraining if they want (which is
| essentially pinning the model version to current), we can do
| model version rollbacks on our side if we see an issue or if
| requested but it's not a self-serve feature yet. Because we've
| made it easy to create or fork a Shaped model, we've seen
| customers often create several models as fall-backs that rely
| on more static data sources or are checkpoints of a good state.
| yding wrote:
| Congrats on the launch!
___________________________________________________________________
(page generated 2024-08-13 23:00 UTC)