All Forum Posts by: Jason Ling

In Joe Fairless's interview with a 1031 exchange expert here it seems like you can 1031 out of an LLC that holds a property.

He suggests that it is possible to do a 'drop and swap' where the LLC becomes a TIC with all of the LLC limited partners..

Thus allowing each individual partner to either 1031 or cash-out.

Is this not true?

@Christian Wathne

>>There are so many problems with relying only on an algorithm to make investing decisions; some of them include

Yes, there are problems. If there were none then I would assume that the problem would be solved by data scientists far better than I.

What I want to discover, for my own, is why the problem been solved. If the answer is that you need to bake in localized assumptions and knowledge into your model and there are many many localities where the knowledge and assumptions change over time... Then I could see why Zillow/Redfin haven't cracked this problem. It's an incredibly difficult problem to solve on a national level - but it is solvable at the city or zip-code level.

>>All of these things, and many more, provide huge impact into market value, and today that data does not exist.

Yes, although I'm not sure about huge. I've seen many notebooks that show very strong correlation between sale price, square foot, basement size etc.. Although there is also a strong correlation between "house condition" and "sale price".

>>Do you really think zillow/redfin/etc aren't working on this problem and working hard at making their estimates better? 

I know they are working this problem, they've posted a Kaggle competition with a 1.2mil bounty for those who can help them minimize the log(error) of their estimates. They're providing a 2k sample dataset for the L.A area I believe.

>>ML was not invented yesterday.

I know, ML is a bit of a misnomer. It's mostly regression techniques and a lot of those techniques have been around since the 70's.

>>You're all disillusion if you think you can just plug some off the shelf public data into some off the shelf software and ?>>think you're going to change the world or at the very least gain a competitive advantage.

No need to start making it personal. Let's try to keep the tone friendly and conversational - nothing will get done if the conversation degrades into name calling and tearing each other down.

But no, I don't think you can solve the problem completely by plugging it into some off the shelf software(? To clarify, we're writing the analysis code in R/Python and porting it to C if the idea proves through).

As far as thinking I'm going to change the world - That's beyond the scope of the conversation and now we're getting into hyperbole. My original goal is to answer the question

"Can I write software to predict the price of a home given freely available data?"

You might say, "Well Zillow and Redfin fail and so will you" and my response with that is that I'm completely comfortable with failing because

1.) I will gain insight into the application of data science techniques towards real estate investment

2.) I will make myself more marketable as a software engineer regardless of whether I succeed or fail

>>Try creating an automated system that will fly a drone into a house, analyse it and come up with rehab budgets; you >>could sell that for billions if you could make it work, but good luck

I'm not prepared to make the capital investment needed to make that work. ML towards REI using available data is a side project I can do on nights and weekends - and I'll likely know whether the problem is worth pursuing in < 18 months.

Involving hardware (drones) and image recognition would require capital expenditure and would make the task far too large for a single person to tackle.

@Elbert D.

>>If by some miracle someone can develop a program to see current pics of the insides of homes via VR or some kind of technology than I would be very scared if I was a agent.

Affordable VR is just starting to become available with "Google DayDream". Commodity 360 degree cameras are available on the cheap these days, I think Samsung sells one for ~$150 and GoPro is releasing one soon.

Superficially it seems like you might be able to use project Tango to create a 3d model of the inside of the home...sort of.

You still have to provide textures and things - so I think real estate agents are safe for at least a decade.

>>But then again software/digital tech will replace a lot of jobs.

Yes, but truck drivers, taxi drivers, radiologists and grocery store clerks have a lot more to worry about in the short term.

Truck drivers/Taxi Drivers = Everyone and their mother is going for level 5 autonomous driving. I'd expect to see some big things in <7 years.

Radiologists - Seems like easy pickings for ML. Radiologists would still exist, you'd just need far fewer of them to do the same amount of work.

Grocery stores - Last I heard Amazon set up a "employee-less" grocery store pilot in Seattle some time last year. You go in, pick up your groceries and leave and you get billed for what you bought. Combine that with the fact that Amazon just bought WholeFoods. Honestly Amazon scares me, they're definitely not the good guys, they are ruthless.

@Jon Cooper 

Thanks! I'll keep an eye on the Kaggle comp.

@Severin Sadjina

Also did you write your own algorithms or did you end up using pre-canned ones? e.g sci-learn?

I'm probably going to be using Octave to develop my approach, rewrite in Python for better performance.

If I really need to scale then I think I'll start looking into Go or maybe even C/C++ .

@Severin Sadjina

>>10k samples sound pretty good! Is that only one type of real estate (SFH...?)

That's single family homes, in popular metro areas I am confident I can easily achieve 10k sample data/10km^2 - maybe more. But the older the sales data the less likely it is to be described with the same model as homes sold today.

>>but I am pretty certain that other types of housing are sufficiently different to require using different models

My hope is to replace human intuition and bias with something more concrete. Right now we classify different residential assets based on a criteria of use and size but perhaps clustering will reveal classifications that people have not realized! 

>>What do you mean by "the median error was 5% but the standard deviation was 20%"?

Say I created the model, the model looks at a property whose price we are trying to estimate. It grabs all other properties sold within 6 months and are less then 0.5 miles from it, I call this my comparison property set.

For each item in comparison property set I compute price/sqft and place these values into a list.

I pick the median from this list and multiply this median price/sqft against the sqft of the property that I am trying to estimate.

I yield a value H. I do this for all properties.

Then I do this where H = predicted value, Y = actual value

percentage_error = abs(1-((H-Y)/Y))

I put these numerous percentage errors in a list.

I take the median and it yields ~5%

I perform a sample standard deviation on the list and it yields 20%.

I interpret this to mean that roughly half of my estimates over estimate the price by more than 5% and the other half do better than 5%. How much I over-estimate by 5% is hinted at by the standard deviation of 20%.

I assumed that my error % was normally distributed (I did not check) - and given that my sigma (standard deviation) is horrendous. If it were something ridiculous like 2% or 3% - I would then be very happy with this model and would question my motivation towards seeking a better model using ML.

Note: I did compute the error rate for various distances and history length (e.g I used houses within 0.25 miles, 0.5 miles...10 miles) and 5% was the best.

I'll have to look more into NN but my first approach would probably be to use some ensemble method.

As I understand it ensemble is to use multiple weak learners in a network to yield a strong model. I myself do not know much about it and I have some studying to do.

My hope is that ensemble would effectively create a custom hypothesis for me - right now the biggest challenge I see is to pick a good H(x)! I want a good way to pick H(x)!

@Severin Sadjina  You wrote So the point is: one could maybe pre-train on, say, ALL SFH in the entire US market, giving a huge data set, and then use that knowledge to further "specialize" on the local markets. I wouldn't be surprised if that is already part of what Zillow is doing by the way...

Yes, this is what I was thinking. Of sub-dividing regions into properties that behave the same way. Maybe using some clustering technique.

Of course you would allow clusters or groups to evolve and change over time.

I think some powerful insights beyond the price of the property could be had! Something that human intuition alone could not guess at.

@Severin Sadjina -Hey Severin, I'm just starting in ML and haven't gotten quite to neural networks yet. I was principally going to try regression techniques or ensemble methods for predicting home prices.

I do however, have a pretty healthy data set. With little effort I was able to obtain a training set of 10k samples for about a 20km^2 area. I believe I can get even more.

I tried to use a simple non ML algorithm by using median price/sqft but my results were poor, although my median error rate was <5% the standard deviation was 20%! (Assuming normal distribution for error rates, this is quite bad..almost useless!)

Is there a reason why you just stopped with linear regression (I don't know much about neural networks yet). Why not use ensemble methods?

Doesn't linear regression imply that there is a simple linear relationship between price and features?

@Andrew Johnson - I think that ML would be able to meet or beat blind appraisals (depending on the ML practitioner's ability). I think ML would be less useful if a significant portion of the information was hidden (e.g required you to inspect the property visually).

But you do have a good point with the permitting, I had the same intuition. 

That the age of the property and the number of permits may indicate the health of the property.

All of this information could be fed into a ML model.

The strength of ML is that the computer will be able to analyze thousands if not tens of thousands of deals per second and it is possible to have notification of a deal within hours of it being available.

Thanks Vivek,

I'm not quite good enough to be paid 1M a year (10 years experience as a software engineer, but only started studying machine learning for about a month) - but I'm interested in machine learning enough to use REI as a "practice project".

If my practice yields something of significant value - then all the better! 

If not, at least I'm acquiring real life practical experience when it comes to data science.

@Vivek Khoche - Thanks Vivek, it sounds like you're saying that the great deals are rarely made public and deal finding happens mostly in off market transactions? If that's the case then yes, machine learning would be of limited use.

Machine learning can only use publicly available and digitally published data to find deals. If it's true that no great deals ever make it to MLS listings or craigslist listings (or whatever) then yes, I agree, no amount of machine learning could ever help!

I would then turn my efforts on trying to predict when a homeowner is willing to sell their property in an effort to try to seek out off-market deals before anyone else is aware of them.

That however, seems like a much much harder problem to solve!