Real Estate


How to Solve the New $1 Million Kaggle Problem - Home Value Estimates

#artificialintelligence

More specifically, I provide here high-level advice, rather than about selecting specific statistical models or algorithms, though I also discuss algorithm selection in the last section. If this is the case, an easy improvement consists of increasing value differences between adjacent homes, by boosting the importance of lot area and square footage in locations that have very homogeneous Zillow value estimates. Then for each individual home, compute an estimate based on the bin average, and other metrics such as recent sales price for neighboring homes, trend indicator for the bin in question (using time series analysis), and home features such as school rating, square footage, lot area, view or not, and when the home was built. With just a few (properly binned) features, a simple predictive algorithm such as HDT (Hidden Decision Trees - a combination of multiple decision trees and special regression) can work well, for homes in zipcodes (or buckets of zipcodes) with 200 homes with recent historical sales price.


Predicting House Sales

@machinelearnbot

To impute the value of a house for years in which it did not change hands, I applied the log returns of the Case Shiller Charlotte Home Price Index to the most recent sale price. Therefore, if random forests greatly outperformed logistic regression, I could prioritize feature engineering to help improve logistic regression's predictiveness while still retaining its descriptiveness. By calibrating the cutoff on the logit function to yield a false positive rate of 0.5, we can greatly increase the true positive rate for a subset of households, as depicted in the below tables: If a real estate broker were to use this model, they would be 60% more likely to distinguish prospects from non-prospects. Historical patterns could instead be used to look for inflection points where next year's sales may be less predictable based on this year's data due to a potential change in macro factors.


Alphabet's Sidewalk Labs Eyes Toronto for Its Digital City

@machinelearnbot

Sidewalk Labs LLC, the urban innovation unit of Page's Alphabet Inc., has applied to develop a 12-acre strip in downtown Toronto, responding to a recent city agency request for proposals, according to two people familiar with the plans. Before applying in Toronto, Sidewalk Labs discussed creating a district in Denver and Detroit with Alphabet executives, according to the people. In a speech last week at the Smart Cities NYC conference, Sidewalk Labs Chief Executive Officer Dan Doctoroff said the firm is exploring development of a "large-scale district." So far, the most visible project is LinkNYC, a network of ad-supported Wi-Fi kiosks in New York City run by Intersection, a Sidewalk Labs investment.


Startup Vacasa Is Utilizing Machine Learning And AI To Determine Vacation Rental Pricing

#artificialintelligence

While Airbnb brought enormous attention to the short-term vacation rental space, more specialized players are now entering the industry, bringing differentiated offerings to a new trend in hospitality. The new dynamic pricing technology, Yield Management 2.0, will set pricing for more than 5,000 vacation rentals across the country. Yield Management 2.0 is leveraging machine learning models consider diverse factors in near real time when determining where to price a vacation rental. "For years, Vacasa's pricing algorithm has secured maximum returns for our homeowners while providing competitive rates to guests, and Yield Management 2.0 takes this to the next level," Breon added.


Machine Learning is Fun! – Adam Geitgey – Medium

#artificialintelligence

Instead of writing code, you feed data to the generic algorithm and it builds its own logic based on the data. To build your app, you feed your training data about each house into your machine learning algorithm. Unfortunately "Machine Figuring out an equation to solve a specific problem based on some example data" isn't really a great name. It would mean that in every case, your function perfectly guessed the price of the house based on the input data.


Rentberry's controversial property bid site expands in US

BBC News

And he reveals a new feature: in the coming weeks Rentberry will implement a machine learning system that will analyse local rental market data to help landlords set reasonable prices. It will also try to rate prospective tenants for landlords based on information that Rentberry has about them, such as how many years they have been working. Mr Lubinsky also points out that the site requires bidders to submit personal information such as their social security number in order to take part in an auction - an effort to stop people trying to drive up the cost with false bids. That might not be enough to satisfy some of the more traditional property managers, suggests New York estate agent Douglas Wagner at Bond New York.


This Real Estate Startup Is Exploiting Zillow And Airbnb's Blind Spot

Forbes

Revestor is a real estate search engine that lets users run investment calculations over live listings. Founded in 2011 by Bill Lyons, Revestor is a digital real estate search engine that uses proprietary data and live listings to help sync realtors and potential investors with desired residential properties. While other services allow users to search real estate based on specific property details, Revestor lets users search based on investment criteria. Revestor's competitive advantage is found in the platform's emphasis on customization, providing in-depth analysis tools to assist beginning and experienced real estate investors find potential investments nationwide and accurately measure their likely return.


NewsFactor Tech News - Mobile Edition

#artificialintelligence

Chatbots are artificial intelligence-powered virtual assistants (VAs), found within messaging apps or websites, that automatically respond to consumers' requests and provide information via chat or text. "Chatbots can provide immediate responses and property information to interested buyer and seller inquiries and help tee them up for real estate agents to take over," said David Tal, CEO of Agentology, a San Diego-based tech company that provides lead qualification services for agents. "They also save real estate companies from the human cost of having full-time staff calling and responding to many inquiries that a chatbot can understand and assist with." "Having a chatbot automatically respond has increased lead responsiveness and allowed me to follow up with more leads," said Weaver, who uses products like Riley and Purechat that function as a cross between chatbots and VAs.


Property Management May Be The Next Frontier For AI

Forbes

The growth in rental demand has resulted in strong demand for property management services, and the property management industry has grown to $73 billion a year. Zenplace, out of Silicon Valley, provides full-service, national property management services to property owners, institutional property portfolios and property managers. Despite the large size of the professionally managed global real estate investment market ($7 trillion), the sector has lagged behind in technology. With these innovative companies making property management easier, property owners can increase returns, reduce costs, better maintain their properties, improve the tenant experience and have peace of mind.


Know Your Industries: 70 Market Maps Covering Fintech, CPG, Auto Tech, Healthcare, And More

#artificialintelligence

European Banks are under attack from a number of emerging specialist FinTech startups. Here are some of the European FinTech startups unbundling banking. Our market map showcases the thirteen most populated markets comprised of private companies valued at $1B as of 01/20/17. Five cybersecurity unicorns valued at $1B are represented in this map including: Okta, Lookout, Avast Software, Tanium, and Cylance.