PropMix announces nationwide coverage of Public Records data – residential and commercial

PropMix has completed the acquisition and integration of nationwide public record data on residential and commercial properties. The data covers additional property attributes such as owner occupancy, last sale information, and more detailed tax assessment information along with full property details. It also provides property identification, seller/buyer information, tax exemption details, building information, and legal description of the property.

This increased coverage enables PropMix to provide Public Record data alongside listing data, thereby creating a comprehensive information source for appraisers and valuation experts. The enhanced dataset also supports a larger coverage of the Uniform Appraisal Dataset (UAD) specs used in the mortgage underwriting process. Valuation models and comparable similarity scoring are now based on authoritative property details and current market conditions from listing data.

Assessor data


Another highlight of this new development is the added features in PropMix products Market Conditions Advisor and iCMALive, our CMA platform. Both the products now offer optional features enhanced by public record data such as comparable scoring using public record sales and listings. Data population tasks are further automated and data accuracy can be validated within the application, giving the user more flexibility and speed.

Stay tuned as we continue to innovate and deliver more features to the market in the coming weeks.

Effective Lead Generation for Agents and Brokers

As a Real Estate agent or broker, generating sufficient leads is critical to sustain and grow your business. It is imperative that agents and brokers identify innovative ways to attract and engage their customers. Providing a home’s value is a good way to raise the curiosity of any visitor to a real estate website, and keep them engaged with what you have to offer.

PropMix can provide a white-labelled, cost-effective home value solution for your website. Each listing will have a button next to it for the fair market value for the property. Upon clicking the button, the user is prompted to provide their email id where they wish to receive the home value report. The address of the property and other details are pre-filled to make it a very convenient way to fetch the home value report. Once the report is generated instantaneously, an email is triggered to the customer.

Effective lead generation for agents and brokers

Agents will be able to log in to iCMALive to view the details of the property and the customer, as well as the home value report that was generated. They also have the option to edit the report to fine tune it, and make the updated report available for the customer to view. The dashboard on iCMALive provides a quick view of all the leads generated, along with their current status. As you are aware, a quick follow-up with the customer will ensure a better closing rate for the leads generated.

As a Broker, you have several options to route the leads generated. You could assign a specific geographic area, such as a postal code, to an agent. Another option is to assign the leads in a round-robin fashion among the agents available. You can also re-assign leads based on availability of agents, or if the leads have passed a certain duration without follow up.


How do you leverage local market conditions to gain competitive advantage?

Every Agent in your neighbourhood would have anecdotal evidence about recent listings and sales. However, it is hard to accurately gauge the trends without actual data. There is an overload of such data these days, but how do you gain insights into the market trends from this data set to focus on the next growth driver for your business?

Customers, both sellers and buyers, have started demanding more data based analyses of the neighbourhood. Your ability to provide data points is diminishing by the day as they get more and more of that information from online sources. As a Real Estate broker, have you attempted to leverage local market conditions to gain a competitive advantage?

Leverage local market condition


With PropMix, you have complete visibility into changes affecting your market, and how these are impacting as you move through the real estate cycles. Our leading nationwide real estate data and the analytical solutions built on top of that will give you the solutions that you need.

Our in-depth analytics provided through Market Conditions Insights (MCI) can help you not only provide valuable insights on the price-trends in your local market, but also predict the trend for the next two quarters based on lead indicators.

We will help you define the parameters that you have defined as critical for your market. These parameters are then processed for the last 60 months, and the trends are made available to you in a format that makes it easier for you to consume internally, as well as make it available to your customers or on your reports and website. The customizable widgets can be fine tuned to provide the insights that are most relevant for your customers.

Predictive Analytics to Grow Your Business

As a Broker, you are always on the lookout for better strategies to grow your business. Advancements in recent years have provided a wide variety of data on listings, agents, geographies, market trends etc. But does your current analytics platform automatically provide you actionable recommendations on how to grow your business? Can it alert you to a new business tactic or strategy?

Leveraging analytics to grow your business_02

PropMix’s BrokerView uses big data and deep learning models to analyze your historical and current transactions and marry that with market and competitor predictions in your area. We can discover your business practices and generate highly targeted recommendations on neighborhoods, markets, market segments, and agents.

Our analytics based agent and office performance management solution helps you identify the best agents, which geographical areas to target, and where competition is gaining market share.

The Office level dashboard helps to monitor total leads captured and tracked, while the Agent level dashboard measures each agent’s lead activity. The analytics section provides the following insights through intuitive graphs:

– Year-on-Year trends on # of Listings & Sales

– Year-on-Year Commissions, Sale Price, Sold Price per Sq. Ft.

– Trend of homes sold compared to Inventory

– Trend of Sold Price to Median Price in the market

–  Average Time for Contract to Close

–  List to Sold Price Ratios

–  Buy-Side Price Performance

–  Median Sold Price


How do I use Sally to Label an Image?

How do I use Sally, the cognitive image advisor, to label an image in my application?

Using Sally to label an image is quite simple. All you need is to make a POST request to the Sally API as given in the example below. Sally has been trained on Real Estate specific images and continues to improve its accuracy as more and more images are used for training the application. Read more about Sally here.

API Request GetLabelsForImage

POST Method:


Body: {

“imageurl”: “”,

“accesstoken”:<< your access token goes here >>


Header: Content-Type: application/json

A sample image is given below.

The API responds with the image label. In this case, the API identifies the room as a Kitchen.

API response


   “status”: {

       “code”: 200,

       “type”: “OK”,

       “message”: “Success”


   “imageAnalysis”: {

“imageName”: “kitchen_001.jpg”,

“imageInfo”: [


               “labelName”: “Kitchen”,

               “confidence”: 0.922417





Interested in trying out Sally in your application? Click here to get a trial access token.

How do I use Sally for room-by-room comparison?

A user guide for testing Sally at

Sally is a cognitive image advisory service that identifies property information from listing images. Sally automates the analysis of listing photos to:

  • Identify types of rooms – kitchen, family room, dining, game room, basement, etc
  • Identify objects in a room – brick fireplace, type of refrigerator, type of counter tops, number of sinks, etc.
  • Extract detailed property information from the photos

Sally is a neural network engine trained on terabytes of real estate imagery and it continues to learn how to perform deeper analysis. After an initial 3-month training period Sally started classifying images into different room types. After another 6-months of rigorous research, redesign, and retraining, she can now pickup objects in a room to help improve your listing data.

How do I access Sally?

You can access Sally using the URL No login credentials are required to access the trial site.

Are there any restrictions during the trial period?

During the trial period, Sally will allow you to search only for properties in the zip code 33156 in Miami, FL.

Home page

The home page of Sally is shown in the screenshot below

Enter an address to search

The Address field in the top left cornet can be used to enter an address. The possible addresses in the US are prompted as the user types the address. For the trial period, the addresses within zip code 33156 in Miami, FL can be used. You can also start with the address that is already pre-filled in the Address field.

Once the address is entered, the app requires the user to verify the address components of the Subject Property as given in the screenshot below. The filter criteria for the search can also be specified in the filter area in the top row.

Search results

The search results are shown in map view and table view as given in the screenshot below

Grid View of Search Results

The user has the option to select the Grid view of the property details section on the right side. The view is as shown in the screenshot below.

Selecting a Property for further analysis

Clicking on a pin or the property card in the right side will highlight the property on the map view along with a summary of the property details.

Select properties to compare photos

You can add up to 5 properties to compare photos with the Subject Property by clicking on the Add to Compare button next to the Address on the table view or on the thumbnail on the Grid view.

Comparing photos of selected properties

 The photos of selected properties can be compared by clicking on the Compare Photos button on the top right corner of the page. The images of the properties categorized by type, such as Exterior, Bedroom, Bathroom, Kitchen etc are displayed as in the screenshot below.

Removing a property from the compare photos view

A property can be removed by clicking on the Delete icon next to the Address of the property


Sally API Technical Details

Sally app uses two cognitive APIs – GetListingsByRadiusWithThumbnail and GetLabeledImagesByListingId

  1. GetListingsByRadiusWithThumbnail

GetListingsByRadiusWithThumbnail API returns the comparable listings within the given radius along with thumbnail images. ImageType can be passed as Input Parameter, example &ImageType=Frontage. If the input ImageType is available in the data then the API will respond with corresponding thumbnail image of that property, else the Thumbnail will be displayed on the basis of predefined priority.

API EndPoint:


  1. GetLabeledImagesByListingId

GetLabeledImagesByListingId API returns the ‘ImageUrls’ along with the ListingId, categorized on the basis of image type. For each image, corresponding image labels are also identified and displayed in the response. Up to ten ListingIDs can be provided in the same API call, separated by comma.

API EndPoint:


Sally API Documentation

Sally API documentation is available in the PropMix API documentation page under Insights APIs for GetListingsByRadiusWithThumbnail and GetLabeledImagesByListingId.

Recent Trends in Using Computer Vision for Real Estate

Computer Vision can be broadly defined as the processing of images so as to interpret the objects contained in them. With recent advancements in image processing, machine learning, and cognitive computing, computers are able to simulate the human visual sensory process to a large extent. The advancements in these areas in recent years have helped computer vision reach maturity levels that are several orders of magnitude advanced than what was possible even a decade ago.Computer vision is widely used in several industrial and consumer applications today. Face recognition for accessing a personal computer, tagging individuals on photos, use of robotics in manufacturing automation and quality control, analysing patient condition through remotely uploaded images, home security solutions that distinguish familiar faces from those of strangers, etc., all apply the concepts of computer vision. Autonomous, smart cars and associated technologies rely heavily on sophisticated computer vision algorithms that are still in the advanced stages of development. With the seemingly unending possibilities that computer vision offers, it is only natural that billions of dollars are invested in advancing the boundaries of this technology. The amount invested is expected to go up from USD 7 billion in 2015 to USD 50 billion by 2022, at a CAGR of 30%+ .

How is Computer Vision relevant to Real Estate?
Technology related to computer vision is making inroads into all areas of human interest, and Real Estate is no different. The recent advancements in computer vision are helping players in the industry unlock areas which have hitherto been considered impossible to achieve as a scalable solution. With the availability of significant computing power at costs that are getting reduced every quarter, the applications of computer vision is expanding at a fast pace in the industry. Some of the important applications of computer vision in Real Estate are given below.


  • Unlock listing data through photos
    According to a blog from , computer vision can help reveal hundreds of property attributes from listing photos that are typically not captured as part of the listing information. Users will now be able to understand factors that are subjective, such as the quality of natural light and vastness of the view without even stepping into the property.
  • Transform listing search to searchable images
    Users would be able to list properties using specific image characteristics, rather than what has been traditionally done using quantifiable property attributes such as beds, baths, living area etc.
  • Identify matching properties quickly
    Image based search would be able to identify properties that display similar characteristics on a whole set of attributes. Agents would be able to match properties with nuanced attribute descriptions leading to more productivity and customer satisfaction.
  • Create property details for listing just from images
    In the future, agents would be able to generate entire property details and room-wise amenities list by just uploading a set of photos. Computer vision will enable recognition of the elements contained in these images, demarcate them, and create listing information that can be uploaded directly into an MLS or a listing platform.
  • Sequence property images in a pre-defined order
    Typical MLS listings have photos of properties in a haphazard order which do not follow a sequence. Through computer vision, listing agents would be able to sort the photos quickly and efficiently in a pre-defined order before uploading to the listing platform. By adding image quality filters to this process, photos which are not good can be marked out for replacement or deletion.
  • Compare properties room-wise
    Computer vision can be used to compare multiple properties room for room in terms of space, relative location of windows and doors, natural lighting, etc. Multiple images for the same room, if available, can be grouped for better comparison and assessment. All this is possible on listings that have been entered years ago since images can be processed real-time. This can create a compelling user experience for the property buyer.


Introducing Sally, a cognitive imaging service from PropMix

Continuing on our promise during Inman Connect NYC 2017, we are now moving our image advisor service out of the labs into general availability. It has taken us over 18 TB of images and 3.2 nerd-years to train our neural network to perfection.

Sally – our Convolutional Neural Network (CNN) based deep learning platform for computer vision, has been trained specifically on residential real estate imagery and is now available as a service for anyone to leverage. Sally can look at a set of images for a home and automatically select and recommend the best picture to be your thumbnail and also reorder your photos for the best viewing experience for consumers.

Sally uses a growing library of millions of images available via PropMix to constantly train itself. Sally can now analyze each image and identify not just the type of room – kitchen, living, dining, etc. – but can also recognize what is available in the image. For instance, Sally can easily recognize the image of a kitchen along with the type of flooring, countertop, cooking amenities, shelves, sinks etc. Sally provides a score-based ranking of its recognized objects enabling the higher level algorithms to make contextual decisions for property listings, valuations, and/or fraud detection.

Expect a lot more to come from Sally in the coming months to empower sellers, buyers, agents, and appraisers in the real estate market. Please subscribe here for exciting news on Sally.

PropMix announces variants of CMA Comps insight for better decision making

PropMix has marked the start of 2017 with the launch of its CMA Comps insights and its variants. The enhanced CMA Comps insight looks at more attributes of the Subject Property and the comps, and assigns differential weightage to these attributes based on feedback from industry practitioners.

The variants of CMA Comps insights include Best Fit Home, Similar Homes and Match My Home.

The Best Fit Home helps to zero in on the most similar properties that match a buyer’s ideal home characteristics. The search can be limited to specific geographies – zip code, neighbourhood, school boundaries, or towns.

Similar Homes can be used on any IDX website to recommend other homes that are most similar to a property whose details are being viewed by the viewer. This helps the buyer to short-list homes with ease minimizing the need for filtering and going back-and-forth between search results.

If a home owner is relocating to a new location, Match My Home enables them to identify the properties that are most similar to their current home, but in their new town. PropMix can find their current home characteristics from public records and find homes that closely match theirs without the homeowner having to go through the hassle of specifying each attribute on a website.

Real Estate Lender Portfolio Monitor

Our case study on Portfolio Monitor service is available here. Learn more about how PropMix is helping one of the largest hard money lenders keep tabs on market activity for the properties in its portfolio. Such activity includes notices of default, pre-foreclosure, and foreclosure activity within the portfolio. The alerts are delivered daily for timely analysis and action with no additional overhead on the customer’s resources. PropMix does all the heavy lifting – market data gathering, data management, and business event monitoring.