On their platform, Stokctwits have a variable for each stock called trending score and a dummy for being trending or not. Does anybody know the definition of these? I already contacted the support team, but it seems they are super busy.
Related
How can you launch a new product if you can't run an experiment? Or how can you adapt a metric so you can run an experiment?
Example in this link: https://hbr.org/2018/11/using-experiments-to-launch-new-products
Uber wanted to launch Express Pool, so they do the tipical A/B testing and compare metrics ,but in this case they have metrics to compare before and after launching the product (revenue per user, avg trips per users, etc.)
But what if this is a complete new product? Example: Uber trying to launch a Wallet?
If I don't have a counterfactual, what can I do?
There are multiple things you can do before launching a new product.
You can run survey for different groups of users asking the about their needs.
The scope of this survey is to identify problems that you can then solve using your product. This is a very early age tactic you can use to determine if your product has a potential fit into the market.
You can create pitches and crowd-founding campaigns
The scope of these are to determine if there is a potential demand for your solution in the market. You are basically starting to sell in the idea phase, before even getting to build anything. Note that you don't want to scam people here, you are just trying to determine if there is a potential in the market.
You can launch an alpha or beta pre-release version of the product.
The scope of this pre-release is to invite few users into your early application and get their feedback. Based on the feedback you get here you can either improve/ change or update your product before launching it.
You can launch an MVP (minimum viable product) and then track KPIs in the real world. The MVP can give you enough information so you know where to go. Just make sure that you are tracking the right KPIs
Good luck!
You don't always need to come up with specific hypothesis and validate it. Sometimes it's best to understand and quantify how a new feature affects the overall health of your product. A lot of times in the past when we expose a new feature to a small population of users, we'd quickly figure out if everything is working as expected or if there are unforeseen consequences.
This is hard to do without the right tooling. One such tool that provides a holistic view of the product's health is Statsig. Here's a quick screenshot of what to expect when you build and rollout new features (without having to set up a formal A/B experiment).
Disclaimer: I work at Statsig
Been looking at the API docs and was wondering if anyone figured out a way to retrieve the number of followers that are following a specific symbol. It looks like this is possible on a per-user basis (find what symbols they're following) but wasn't sure if there was something like that for symbols.
Thanks all
Currently the follower counts are not available in the open API. They are available to our partners that license the extended data. Sorry about that. If you are integrating into a paid product for your customers, we would love to talk and make not only followers data but sentiment and more available. Please contact us.
I looked at the API documentation and it was not immediately apparent to me. Is it available via partner access?
Also, the default rolling average for sentiment seems to be 7 days. Is there an option to change this. One obvious way of doing this is parsing the firehose and some partners probably do that. I don't care for all that data or parsing it, in the unlikely scenario where I can get access to that.
The Sentiment data is only available to partners that license our API. Please touch base with us and let us know what you would like to do and about your paid product:
http://stocktwits.com/developers/contact
There currently is no option to change the rolling average, we have plans to add different time frames, as we agree this would be helpful.
We offer a financial sentiment API at Knowsis.
API docs are available here: http://knowsis.github.io
In google's prediction api page, it says we can use it for recommendation of webpages / products...
Can someone please show me how, for example:
I have 500,000 members purchased history
I have 2,000,000 products in 200 different categories
I have user-X just signup, asked him 15 'like' / 'dislike' product questions (user's taste)
Now, i want to suggest/recommend user-X with a list(e.g. 500) of products which he most likely willing to purchase
Thanks a lot
If you are not specifically tied to Google API fow whatever reason, explore using Mahout. This is a basic use case for the Mahout Recommendation mining.
https://cwiki.apache.org/MAHOUT/itembased-collaborative-filtering.html
The Google Prediction API, as currently implemented, is great for classifying data into a discrete set of categories, however, as noted in the documentation:
Avoid having a high ratio of categories to training data in categorical models.
Try to have at least a few dozen examples for each category, minimum.
For really good predictions, a few hundred examples per category is
recommended.
The Prediction API's classification doesn't work well when the ratio of categories to examples is high and in the example you sketched the relationship is one-to-one because you are trying to find the user whose liked product list is most similar to the user of interest (to find a set of promising products to recommend). In this model, each user is a unique category.
I'm putting the required meta-tags into my pages and I have a list I saved from facebook's documentation at https://developers.facebook.com/docs/opengraph/#types
Two problems. One is that my list of business types is, in total:
bar
company
cafe
hotel
restaurant
which is a little crazy. Every type of commercial entity in the world can be categorised as one of those five things? There's not even "store"?
That list is confirmed by this page: http://www.netmagazine.com/tutorials/optimise-your-website-facebook but my second problem is, Facebook no longer seems to be providing a list at all. The documentation says it was updated a month ago.
The tutorial holds out the interesting promise that "Facebook says that it will actively monitor the most commonly used types and add them to the list of supported og:types in due course." so it seems I can make up my own, say "store" or "supermarket" and that won't be an error.
What good or harm will it do to make up my own? What does Facebook use this metadata for anyway?
According to the .NET link article you provided, these are the types you can use:
Activities
activity
sport
Businesses
bar
company
cafe
hotel
restaurant
Groups
cause
sports_league
sports_team
Organizations
band
government
non_profit
school
university
People
actor
athlete
author
director
musician
politician
profile
public_figure
Places
city
country
landmark
state_province
Products and Entertainment
album
book
drink
food
game
movie
product
song
tv_show
Websites
article
blog
website
Now, the list is limited of course, but you can keep it generic by stating something like og:type="website" - it may sound stupid and obvious stating website as the type, but remember tht the web isn't just about web pages - there are all sorts of media to consume.
Or, as you mention, make up your own. If you're sensible about it and specify something like og:type="ecommerce", over time, this may be something others are using and will therefore become a popular choice; with the hope it becomes adopted. If it doesn't, then there's no actual harm that can come of it.
In reality, it doesn't matter what you put there and I suspect Facebook only specifies these types because it wants to know what it's working with for its advertising activities.
But Facebook isn't the only medium that will use these tags, so don't be locked into their methods only. It's best to keep it logical and sensible.
Hope this helps.