All Forum Posts by: Severin Sadjina

Hi everybody!

I have used machine learning (ML) to build models that estimate values/prices for apartments and to predict the expected gross monthly rental income. I did this for my local market (Ålesund) here in Western Norway, but also for Oslo. I also focused on only apartments because that was the most relevant to me. (And no one rents houses in Norway, everybody buys.)

There is a ton to talk about here, so I'll just dive right into it and try to give a somewhat concise overview. I hope this will spark an interesting conversation ;)

So, the biggest challenge has been data volume. It took me a long time to collect over 200 samples in my local market, which is part of the reason I resorted to Oslo (Norway's capital) where I have almost 2.500 samples. Still not a ton by ML standards, but useful.

I used a linear regression model (LR) and a neural network (NN) to model both values/prices as well as gross rental income. For Oslo, I am now down to 6% median error rate (with the NN), and 90% of the test samples are within 18%-19% error rates at the worst. And this is by using only four features (input variables) for the model: living area, year built, and location (longitude and latitude). I am personally quite happy with that. The reason I only use those four is because others (I have a total of 22 features collected, many very sparse) didn't improve my models or made its performance even deteriorate.

I also use principal component analysis (PCA) as a very simple anomaly detection algorithm on the data set. I do this to help me automatically identify properties on the market which may be undervalued.

I know that Zillow's zestimate gets butchered left, right and center. But truth be told, 6% median error rate (also Zillow's national average) is quite good, and probably better than a lot of humans. On average, that is. Sure, it can be off by 20%. But humans can be too sometimes. At least I can. I would also like to point out that 6% median error rate means that, on average, all the stuff that is NOT captured by the models (living area, location, year built) only accounts for 6% of the price.

But still this means that I can't blindly rely on just the models. I use them to help me identify and decide on potential deals. And I can happily report that I just bought my first investment property (a studio apartment right in the city center) using these methods. Personally, I think this is pretty remarkable, because before I started with any of these in March I had NO clue about the local real estate market.

So, what's on the horizon? I have a lot of things I would love to try out. I would love to use image recognition methods to look at pictures of listings and detect things in them that influence the price (a nice kitchen, a pool, a pet elephant, etc.). It would also be great to use text recognition to do something similar. I also want to collect data on more markets to extend my investment horizon (Oslo is useless to me because it is way too hot and expensive, but Trondheim could be good).

Anyway, I would also definitely be up for a dedicated BP ML/AI group and to work together to improve our efforts and models! And I am more than willing to share more details. I'd like to point out, though, that I found ML and data science back in February, so I am far from an expert ;)

Welcome, an thanks for the follow!

Quick follow-up: Pretty much all the people I'd been in contact with earlier that saw the initial price had already found other places anyway. And I am now still getting enough interest at the higher rent, especially as the students will soon flood the market. What do we learn from this? ...well, I'm not sure. But it's probably that people have other worries than one landlord on the market correcting his rent. I'll still try to be more careful next time and set the "right" price from the start.

Douglas Krofcheck 1.) I truly believe that asking for a monthly rent that is spot on with regards to living area, location, standard, and amenities, compared to similar rentals in the area at that time, is the most fair thing anyone could do. I fully agree that it's not ideal for the people that I've already informed about the initial rent, however. Then again, this is my very first rental property. I'm obviously not going to do everything right the first time round ;) What do you believe would be right/fair? 2.) Yes, I would have cash flowed at the initial price. But apparently, and to the best of my knowledge to date, I'd have also (unknowingly) subsidized my tenants living arrangements. 3.) No lease terms were advertised. 4.) I am pretty sure that I can't just raise the rent after only a few months in my country (Norway), but there may be ways around that. I could probably give discounts the first few months. Generally a neat idea, but I'd have to carefully check the legal situation here. Thanks for the input!

Mindy Jensen Removing all marketing and then reposting is a good idea, should have thought about that! Karen S. That makes a lot of sense. Either way, as long as I offer market rent I am definitely good. I mean, what else could be fairer for landlord and tenant alike? Same goes for a more "proper" analysis like linear regression ;)

Just wanted to say thanks for the discussion here. I just bought my first rental property, have already set up a separate bank account for it, and have been using YNAB for my private finances for years (and absolutely love it). So I'll stick with YNAB for now to keep track of my rental(s).

Originally posted by @Account Closed:

Your going to lack credibility with people you already talked with, if your counting on renting to one of them, that matters, for all other potential renters probably irrelevant. Also, expect some renters are smart enough to know setting the correct rent can be tricky in some markets.

I would lose some credibility for sure, yes. Then again, market rents have probably gone up the last weeks/months with the influx of students, so I feel like I should have no trouble backing up my change of mind.

Yeah, nothings been signed yet, and I haven't promised anything to anybody either. I guess my concern is more how I'll be perceived by people as a future landlord if I adjust the asking price like this. Then again, who really cares... :D

Thanks for the input! Guess I am probably overthinking this quite a bit...

Still not sure what to do, but might as well raise the asking rent and adjust later in case I can't find tenants. Making the adjustment would give me over 60% more cash flow, and that sounds VERY good to me.

Hi folks!

Severin, the nerd from Norway here, and I could use some input...

Short version:

Looks like I set the rent I ask for to get my first deal* rented out too low (about 10% under market) by accident. But I already started my marketing campaign and talked to a few potential tenants. Shall I raise the price now? If so, how can I explain? Do I even need to?

Long version:

I just closed on my first deal* and already started marketing for tenants. I've talked to a few potential candidates over the last two weeks, and I started a relatively comprehensive online marketing campaign (Facebook & promotion & Instagram, online rent portals, even giving away gift cards for referrals). I also expect a fresh influx of new and eager students next week when they know whether they've been admitted to our local university or not. So far so good!

I started out asking for 7.250,- Norwegian crowns (NOK) (which is about 885$), and I actually thought that was pushing it. But the location of my property is great (right in the city center), it has a very high standard (built in 2013), and includes heating (important in Norway, as you may imagine), cable TV, and internet with the rent.

So to live out my inner nerd and double-check the price point, I looked at all other comparable rentals out on the market at the moment**, fearing that I may have to lower my rent and miss out on some cash flow.

Well, turns out that I am actually underpricing myself, and that the market would suggest 7.950,- NOK (about 970$). The math is actually very clear on that.**

So the question now is: What do I do? Change all the ads? Explain to the people I already talked to that I raised, and why? Keep as is and miss out on cash flow? I am a little worried I may risk vacancy also (I am not sure how high the demand for high standard studio apartments is...).

So yeah, any input is greatly appreciated! Cheers :)

*) A 270 square feet studio apartment, with a very high standard, right in the city center. Asking price was 1.1 million Norwegian crowns (134.000$), I got it for 1.01 million (124.000$), and I believe it is actually worth closer to 1.2 million (147.000$).

**) Multivariate linear regression, taking into account living area, location, standard, amenities, and which floor it is on. Standard deviation of predictions is only 300NOK (37$), as in, this is a very good model.