JasonCEC

That is very interesting to me... When this first became a business a few years ago, I had hopped that we could get `laypeople` to review products, and then use a mass of consumer data to sell our services.

This has not paned-out in practice; doing reviews on our system is not difficult but it is involved - you have to care about flavor and what you're tasting to do it.

Also, going Standards/consumer route puts us into direct competition with many of the trade organizations that our clients belong to, like the SCAA and the BA - they try to sell their own sensory systems from 'partner companies' (that then donate money back to the organization...).

I think it is better for us to gain the trust of a set of clients who are looking for a better way to taste products for quality control (based on science), and charge them for a service than to gamble on general consumers in the short term. In the long term.... I would love to have 1M+ random people using our app to review beer, coffee, and etc.

[Do you still live in Kunming? // I use to live right around KNU!]

Maybe. We've considered lowering prices - but $500 / month is far less than what any company (startup or not) would need to spend on hiring an employee with quality control experience. We do far more than most QA/QC teams ever could... unless they have individuals with an advanced math degree, expansive analytical chemistry knowledge, and production experience - and paying that team won't be $500 / month!

For anyone interested in starting a brewery, my startup [1] does Flavor Profiling and Statistical Quality control for small to medium sized artisan beer, coffee, and spirit producers.

We use machine learning and data-science to quantify the flavor profile of products, detect flaws, and pinpoint the sources of batch variation.

[1] www.Gastrograph.com

We're a beta client for Shiny Pro. The security features and server monitoring are quite good, and well worth it!

My company uses R, Shiny, and Rserve for nearly everything. R is a great programing language - if you need to quickly and efficiently develop stat's based features for medium sized data.

R excels (get it?) at creating reproducible, fault tolerant, consistent functions that can be automated, packaged, applied to a variety of data types, and then extended later.

Our web-stack is Shiny on AWS and we call our API's built in R (ML, images, data, etc) from Android using Rserve.

A lot of the (programing?) criticisms of R will be 'solved' or become non-issues in the next few years. Multithreading, implicit vectorization, better memory handling, gpu functions, among other things are all in the pipe :) (That said, the syntax _is_ a little weird to get use to)

-----

* We're hiring for very senior positions in data-science and more general R programers. Contact me if you're interested (JasonCEC [at] Gastrograph.com)

[edited for spelling]

If anyone here is interested in improving their home roasting, check out our services for Quality Control and Flavor Profiling [1].

I'd be happy to set you up a free account as a home roaster, and I think feedback from the HN community would be really helpful!

[1] www.Gastrograph.com

My company makes analytics dashboards for Statistical Quality Control and Flavor profiling of artisan products... I think it's pretty good with its filtering options and the like. Link to our first tutorial here: https://www.youtube.com/watch?v=MvHbNcrobwc