Hello Data Blog

The world of online real estate listings is plagued by a major issue - inappropriate use of images with logos or watermarks. Imagine seeing an image of a property with a Century 21 sign in the front yard, posted on the Coldwell Banker website. This not only breeds confusion but also raises credibility questions for the hosting website. The problem isn’t confined to brand mix-ups though – it extends to fraudulent listings too.

When I launched my first startup back in 2016, I wanted to automate all the work I hated doing as a real estate analyst and project manager. Analyzing rent rolls and operating statements, pulling comp data, determining rent growth rates, etc… all of it was time consuming and extremely manual, and I couldn’t understand why the industry worked this way. Our mission was to automate the underwriting process for multifamily properties.

Most real estate companies generate a ton of data through listings, purchase & sale agreements, market studies, site inspections, etc… the list goes on. Large volumes of data can be very powerful for analysis, but in real estate, this data tends to be locked in emails, PDF documents, and Excel models. It’s essentially unusable, unless the data can be extracted in a consistent way. With recent advancements in artificial intelligence (AI), however, it is becoming significantly easier for real estate companies to unlock the value of their data.

Last week, we put together data on the Atlanta rental market as part of a proof of concept with a potential client. The data included rent, availability, concessions, amenities, and many other attributes for about 16k units listed on a single day in May. It also analyzed the listing photos for each property, and included the QualityScore we generated as a variable. I was playing around with the data a bit, and plotted a graph of apartment quality vs average rent by neighborhood in Atlanta:

As Automated Valuation Models (AVMs) have increased in popularity, the valuation of properties at scale has become significantly easier. These models do well analyzing all the data associated with a (usually single family) property and its surrounding market to generate valuations, but they are missing a key capability: Accurately assessing a property’s quality and condition. Traditionally, AVMs have lacked the ability to distinguish between well-maintained properties with incredible amenities, and those in disrepair.

Historical Limitations in Identifying Comparable Properties When I was working at my last real estate tech startup, one of the problems we tried to solve for our multifamily investor clients was how to determine the best comps for any property. It doesn’t matter as much for investors who operate in a single market – they know their comps well. But for anyone looking to invest in a new market, it’s difficult to know which properties are truly most comparable.

In today’s world, where most businesses have shifted their focus towards online channels, having a strong online presence is vital. The real estate industry is no exception to this trend, and having a website with well-crafted search engine optimization (SEO) is essential to capturing more potential customers. Alt text provides an additional layer of optimization that can be used to ensure your listings are seen by the right people. Let’s explore what alt text is and how it can benefit your real estate business.

The Real Estate Data Problem As industries adopt data-driven products, they seem to follow a particular path. First they have to aggregate enough data to actually analyze, then they start leveraging business intelligence products that use that data, then they start using artificial intelligence products trained on that data for better decision making. To analyze anything, you first need a large volume of well-structured data. In real estate, companies like CoStar, Trepp, CoreLogic, Zillow and ESRI laid the groundwork here.

One of the most frequent challenges real estate investors face is objectively determining the best comps for potential acquisitions. In a market with which they are familiar, this may be straightforward – they know the comps because they know the market like the back of their hand. If they want to expand to new markets though, this becomes a bigger challenge – how can they know they are selecting the most relevant comps?

If you’re a tech savvy real estate professional, you know that performing a comparative market analysis (CMA), also referred to as a rent survey for multifamily properties, is essential for determining the value of a property. But what if you don’t have the budget to pay for expensive CMA data sources? Fear not! This blog post will explain what a CMA is, how to perform one, and will provide you with some of the best free sources of CMA data.

Artificial intelligence and machine learning are beginning to have a major impact on the real estate industry. Less than decade ago, real estate professionals had few options for leveraging predictive analytics technology, let alone securing quality real estate data. Now there are products to automatically extract data from documents, pull various property data sources together and even predict investment performance. These advancements have brought more investors into the market and made the industry more competitive than ever.

What is a Rent Survey? If you want to be successful as a real estate investor, you need to make sure you are maximizing the profit from your properties. A great way to do this is through a rent survey, which should be performed for any new acquisition and refreshed regularly for properties you currently own or manage. A rent survey tells you current rents for competing properties in your market, and helps you understand occupancy rates, which amenities are attracting tenants, and where rents are heading.

Should my Real Estate Business Use OCR or ML to Parse Documents (or both)? These days, savvy real estate companies are looking to automate their transaction pipelines, and technologies like Optical Character Recognition (OCR) and Machine Learning (ML) are important in this process. In real estate, businesses need to extract data from documents such as deeds, offering memos, schedules of real estate owned and purchase agreements, and they need to know the extracted data is accurate.

Who Likes Writing Real Estate Listing Descriptions? If you’ve ever read a real estate listing description, whether it was for an apartment or a single-family home, you’ve probably wondered why they are generally so poorly written. Run on sentences, inaccurate information, exaggeration/puffing, misspellings, all caps, etc… the list of things that would make your English teacher shudder goes on. It makes sense though - who really likes writing listing descriptions in the first place?

Why AnyExtract.ai? As a data scientist who specialized in developing algorithms to help real estate analysts and underwriters, I’ve seen a lot of manual tasks performed in real estate. Whether it was observing the process through which clients put market data in their Excel models, or seeing them transcribe transaction data from scanned PDFs into sizers and web apps, it was always a bit painful to see how things were being done in ride-along meetings and requirement gathering calls.

What is Curb Appeal? The attractiveness of a home as viewed from the street, otherwise known as “curb appeal”, is a key factor in minimizing time on market and maximizing competition for real estate listings. The interior design of a home may be incredible, but if the landscaping is unkempt, the paint is fading, or there are cracks in the driveway, buyers may assume there are other maintenance issues inside or in hidden areas.

The Story Behind RealType.ai From 2016 to 2019, when I led the data science team at Enodo, we aggregated data from millions of apartment listings, pulled out unit attributes like beds, baths, square footage and amenities, and trained machine learning algorithms on that data to predict the rent increase from value-add amenities. If you were a value-add investor or developer trying to decide the ideal renovations or features for your next project, we could tell you how much you’d get for those granite countertops, the hardwood floors – even that fancy dog washing station.

Say Hello to HelloData.ai! Extract, Enrich & Predict with Real Estate Data I’m pleased to announce that I recently launched Hello Data, it is an ensemble of solutions for extracting data from real estate documents and websites, enriching it with supplemental sources, and using it for prediction and automation. After working in Data Science for Real Estate for years, I initially used my knowledge to solve my housing problems, and since I had some time to R&D, that eventually became something much bigger.