anmol

Just to add to the other comments, don't let this bother you.

Remember, your goal is to build a solid tech business, not appease YC or anyone else. Not to take away from the value YC and PG add, but there were tech companies before YC, and its just a stepping stone to your final target.

Ultimately, all that matters is (a) awesome product/technology (b) users/customers.

More likely, if the problem you're solving isn't important, talk to real customers or find a friend you trust who will.

I like the UI. any advantages over google alerts?

i.e. analyze our social life, finances, networks, contacts?

Xobni, Skydeck, Mint, and many other popular examples.

Interesting post. Perhaps a few other factors that affect this:

a) sector. consumer web is very different from medical devices or energy. Can't think of any drug or medical device companies that started without a IP portfolio.

a) east coast vs. west coast?

b) age / experience of the entrepreneurs, esp. if they've had any good exits in the past

I'm thinking of the local (Boston) entrepreneurs, who raised $x million from some big-name VC firm for their nth venture, after the first 2 had good exits. The risk profile is very different from that of a 20-something entrepreneur doing a consumer web idea.

very briefly. We're comparing the time + effort spent crafting an application (which apparently is quite large, for first-timers) and not fitting the ask VS simply building it and approaching consumers / partners.

If you have particular insight on any SBIR proposals related to our work, do share. Thanks!

ps. yes, Nathan is a friend.

Once we mockup our UI, would it be possible to have you give feedback / provide suggestions? Could you help us put together a user-trial with say 10-15 tech-savvy parents like you?

pings from device forgotten at home. sorry about typo.

With severely unbalanced classes, overall accuracy is not a good metric. So we use recall of the symptom class, and how it varies with the precision. Recall = 0.6 to 0.9. All results are based on cross-validation.

There is a lot more sophistication we can add (e.g. markov properties), these are almost first-order results.

Nonetheless important to validate with other populations. That would be a big part of testing any product.

The challenge with 'think I've fallen' is that you constantly have to ping the accelerometer. From a battery-life perspective, that kills the smartphone. Also, its hard to distinguish those pings from

For that particular application, its better to use custom body-worn hardware (e.g. fitbit).

Regarding spotting trends in face-to-face networks, we've done similar analysis political opinions during the 2008 election campaign.

Results here: http://web.media.mit.edu/~anmol/political-2.pdf

Thanks for the kind words, and good luck to your family. We really do want to make this into a tool that can help people, if possible.

My intuition is that being able to quantify and visualize 'quality-of-life' automatically, will help support diet and lifestyle changes.

What kind of features/UI would you like to see in such a tool? Would it be better is this was generic (e.g. like Facebook), or something specifically for patients with CF?

Trends are spotted in the first 48-hour window, in our sample. There is the big open question of validation outside the sample population of course.

By precise, do you mean precision versus recall? The tradeoff depends on what you want to do with the inferences. If you send the analysis to say a nurse or family member (i.e., human in the loop, which we think is the right approach) then recall should be optimized.

good idea. we had an initial chat with one of the major ones. They'd like to see more traction of course.

The 90% is a misquote, good catch.

The actual accuracy is between 60-90%, depending on clusters of symptoms, and apparently that was stripped somewhere during editing. Oh well.

The demographics that seem important (e.g. baby-boomers), use mobile phones but not necessarily FSq.

Thoughts? We're thinking of individual-level prediction tools, but there are other ways of using this approach. e.g. at the community / city scale with mobile operator data.

Hi Pg-- were you going to do this soon? we're looking to close on a small round this week...

support the -10 for consulting + ibank + hedge fund. they're all smart guys, but watch out for the ones who have never built a product OR don't like getting hands dirty. although there are always exceptions, jeff bezos came from de shaw.

if this sounds strange to west coast people, at startup networking events in the east coast it is pretty likely you'll run into the 'i've done my gig at mcK/harvard mba and the next step of my career is a CEO position so let me find my awesome tech cofounder' type of person.