Great list, but one caveat I'd add is this: While "SQL will always be faster than your code" is true, in the context of a sufficiently large app with many parallel requests the solution might still be to do some processing in the app because it can scale horizontally and (most) databases can only scale vertically and are thus more limited.
Wheelhouse (https://www.usewheelhouse.com) | REMOTE | Full-time | Design & Front-end engineer
--
We’re a small team of designers, engineers and operators in the hospitality space.
We’re building a revenue management platform for the $500B+ flex rental space. Our technology empowers short & mid-length stay operators, who manage single-family homes, apartment buildings, and (in some cases) hotels - a broad & massive addressable market.
In 2021, our target customer segment voted our platform “Innovation of the Year” at the Data & Revenue Management conference. In 2022, we closed a significant funding round (via many of the best tech, travel & real estate investors) providing us a long runway, low burn, and rapidly growing revenue.
More about us:
As a team, we enjoy shipping products our customers love, on time or ahead of schedule, while balancing work/life & having fun together. Many have worked together for 8+ years across multiple companies. We’re best described as transparent & collaborative, and we strive to set our teammates up for success - both professionally & personally. We’re a remote-first, work-anywhere, and a “yes - you should make time for that adventure/vacation” company.
What we’re looking for:
An experienced (3+ years) front-end engineer with design capabilities. Someone passionate about building great user experiences and who is comfortable taking a design from exploration through to production. Ideally, they can build out designs on their own, or, with partial help from our product designer.
Bonus — Our product can be complex (lots of data, configurations, edge cases), so, someone looking to solve hard problems with a mind for simplified UIs and intuitive experiences would be ideal.
Stack - Tailwind | Chakra | Next.js | Ruby on Rails | Postgres
Benefits - Competitive salary and equity. Full medical, dental and vision benefits for US employees, Fidelity 401K available for US employees, Unlimited PTO, and more.
Wheelhouse is building technology foundational to the growth of the next generation of the hospitality space. We’re a data-driven online revenue management service that helps property owners, hosts and managers understand their business, personal performance, and their local markets and maximize their revenue. Our best in class machine learning price recommendation engine provides highly localized variable pricing and differentiates us from our competitors. Learn more about our research on our blog: https://www.usewheelhouse.com/blog/wheelhouse-pricing-engine...
We’re a well-funded early stage company that has weathered the effects of Covid-inflicted downturn. We’re supported by a number of the best VCs in Silicon Valley, as well as many of the largest Real Estate and hospitality companies in the world. Oh! And, we’re a darn fun team on a path to building a meaningful and lasting company. I can promise you’ll be happy you learned more!
We currently use Postgres, Redis, R, Ruby/Rails, Grape, React, NextJS, AWS - so in depth experience in any of these areas is definitely a plus for any technical role. But we’re always open to new technologies and are just as eager to learn as you are.
We're hiring for several roles, including: Front-End Engineer — Product Designer — Backend Integrations Engineer — Data Engineer
All positions offer competitive salary, equity and comprehensive benefits. We are currently a fully remote workforce but may have an onsite presence in the future.
If you're interested in joining, please reach out to us at careers@usewheelhouse.com
I developed a new incremental learning approach (called IRMA) during my PhD in 2014 and haven't touched that research for a few years. But it has always been on the back of my mind as an approach worth following up on.
Now I decided to make it a bit more approachable through an interactive tool that lets you play with a polynomial that learns from incremental examples you provide. I also included some background on how the method works.
Incremental learning (in contrast to batch learning) poses a unique set of problems as the learning algorithm needs to adapt with just a single new example. Compared to the state of the art, IRMA does this through minimizing what it "forgets" about past learned data while adapting to the new example. I chose polynomials as an example as it doesn't work well with the typically used gradient descent but can be learned with IRMA in a much more stable manner.
The same approach has a closed form solution for a variety of other models (that are linear in the parameters, i.e. LIP) and I'd be interested to try and apply it to more models (like neural networks) or other tasks (like classification) as well.
Interesting, I'll have to dig in some more. I have a similar story with Prioritized Grammar Enumeration (PGE) for Symbolic Regression. It's my PhD work that has been sidelined since 2015 and I've been thinking of resurrecting it.
Nice, I have only limited experience with symbolic regression. But, from what I gathered from the abstract of an ACM paper I found, I like the detour from the usual stochastic approach toward a deterministic directed search. Does that imply it could have problems with local optima, though?
There is a different sense of it, specific to PGE, but not anything like stochastic models. In PGE, the local search operators, those that expand equations (parse trees) by making small additions can get into situations where:
1. a pretty good equation has been found
2. small modifications don't have much of an impact, so it stays good
The solution I was thinking of is to do more bookkeeping and eliminate wasted work like this.
In a sense, you don't really get stuck in the same was as GP / Stochastic algos because of the memoization. You always have to be trying new solutions (parse trees)
Also wanted to explore DeepQ/RL for helping to guide the decisions of what to expand and where to expand it.
We're building a data-driven hospitality company, and data science is the foundation of our success.
Over the last 2.5 years, our team has worked to develop the world's most accurate pricing engine for short-term rentals. We use this pricing engine to power an increasing set of product lines, including Wheelhouse Pricing. Building this pricing engine required (and still requires) us to borrow from a wide range of statistics and ML approaches, including methodologies we found in bio-sciences and other realms.
Now, we're looking to add another data scientist who is passionate about building interpretable machine learning models, and taking them from research to production. These models help our software customers price their homes accurately, and also serve as the foundation of our relationships with many of the world's largest real estate companies.
Our data science team is closely integrated with the engineering team, and we are not shy of full stack tasks from DevOps to front-end integrations. We use open source and homegrown tools in a cloud environment to build the data-driven foundation of all our products.
We currently use Postgres, Redis, R, Ruby/Rails, React, AWS - so in depth experience in any of these areas is definitely a plus. But we’re always open to new technologies and are just as eager to learn as you are.
Same here - actually the Nexus 4 still is a great solid phone. But besides the battery life, storage space for apps is a problem for me. Since the latest Android updates, apps got a lot bigger and I regularly need to delete stuff to be able to get all the app updates.
Maybe it's time for a new phone now.
Since Lollipop it's been agonizingly slow for me. Apps take 4-6 seconds to open, opening a web page can render the phone unresponsive for seconds at a time. My wife's has become unstable, hard-locking and/or rebooting several times a day. Using the camera in particular seems to cause it to misbehave, which is unfortunate as she loves taking pictures.
It's been a great phone, no doubt, and we've loved ours, but it feels like it's time to move on to the next thing.
We use a linear model with binary extension of several properties of a listing to learn the current value of different listings as it is on the market.
We combine this daily with an analysis of how much hosts and hotels are already increasing their prices and whether they book or not to see how much our learned base price should be increased for the Super Bowl.
The dataset is based on publicly available data from Airbnb and Homeaway.
"We use a linear model with . . . . . " ... that's what most HN'ers clicked the link for; and not to actually search listings. I wish you had linked to a nice, long nerdy writeup about the product, instead of the product itself (which, while interesting in general, is not as much for this crowd).
Great call on sharing a more robust write-up. We're going to be watching the market closely over the next 10 days and will share more here.
For our team, one of the more interesting aspects of continued observation will be a more fine-grained understanding of price elasticity around such a major event.
