Skip links

PROPTECH-X ‘Proptech & Property News’: Ascendix – Why traditional property search needs updating | Does Generative AI mean the end for content creators?

Ascendix – Traditional property search and what’s wrong with it?  

I have spent every day for the past seven-years pushing for the digital transformation of real estate, digitising analogue legacy systems, so it is great to see Ascendix shining a spotlight on all that is wrong about the usual clunky property consumer search journey, and how to fix it. The following excellent analysis was written by Ascendix’s Yana Yarotska.

‘Property search is usually a hard task requiring plenty of effort, research, and time. To accomplish this, the majority of modern rental marketplaces offer keyword search in combination with filters and Geo-search. But if future tenants are not sure about what exactly they want, or are just browsing, these search approaches simply do not work.

Imagine if users could talk to the search bar, just like they talk to ChatGPT, and get results that fully match their needs. It would be like having a conversation with a friend who understands exactly what they’re looking for. AI-powered search and Natural Language Processing algorithms do just that. In our article, we explore how this process happens, and investigate AI search from the perspective of a customer and the technology behind it.

Most real estate portals and booking websites employ a combination of keyword and faceted search (filters and sorting), e.g., or Airbnb, with the addition of Geo-search. While filtering involves toggling through property criteria, keyword search aims to precisely match user queries with website content, akin to using a book index.

Traditional Filter Search | Source:

Despite being straightforward and familiar to users, these search algorithms may not always be effective in the real estate context. For keyword search, for example, obvious drawbacks are:

Lack of context. Keyword search rarely has the ability to understand the context, leading to potential misinterpretations of the query, and, therefore, irrelevant results. For instance, the real estate term ‘flat‘ may refer to an apartment, a characteristic, or informal pricing, leading to potentially irrelevant results.

Limited understanding of user’s intent. It may not adapt well to changes in user intent during a single search session, consequently leading to results misinterpretation. This way if you searched for ‘London parks’ and then decide to find a place for your car to ‘park in London,’ you are likely to see more green spaces, instead of places to park a vehicle.

Insufficient results for long queries. If the user learned a lesson and decided to include extra details in the query, surprisingly it may fail just as well. Extremely specific or long-tail queries may not yield accurate results, as the system will struggle to match the exact combination of keywords entered by the user. Apparently, if you are looking for a ‘three-bedroom family house Virginia parking garage,’ only a few of your requests will be fulfilled in the search results.

Inability to understand language variations. Keyword search may not account for synonyms, alternate spellings, or variations of terms, potentially causing relevant content to be overlooked. Ambiguity in the keyword query which has multiple meanings often leads to irrelevant results, and even punctuation may cause trouble. So, ‘2 bathrooms house Dallas’ and ‘two-bathroom house Dallas’ can have very different search results.

Dependent on the query quality. The quality of search results heavily depends on the accuracy and specificity of the keywords. Users who use vague, ambiguous, or not very specific terms may struggle to find the desired information. Golden mean between clarity and conciseness is a must when dealing with keyword search, but it may be troublesome to reach.

Filters and sorting conversely have the following drawbacks:

Limited flexibility. With filter search, the user can only choose from pre-defined categories of properties, available on the marketplace. This way, there is a limited possibility of customized and personalized choices. The user cannot insert their own filters from the very beginning but has to look for the appropriate ones by scrolling down through a lengthy list, which means more time and effort spent on the search.

Manual, time-consuming, and tiring. Filtering your way to the dream property may be tedious, lengthy, and boring: because of a huge variety of filters on marketplaces, the user is likely to spend a lot of time scrolling through options while searching for the appropriate place for rent.

Natural language search is an AI-powered search that can understand and process queries in natural conversational language, rather than in specific keywords or structured filters. In natural language search, users can input the query using everyday language, either by typing or saying it, and the search engine in AI for real estate uses advanced language processing techniques to comprehend the context and intent of the query to provide the most relevant results.

Natural Language Search in Practice: Ascendix AI Property Search Example  NLP search uses advanced technologies of deep learning and natural language processing to understand queries written in a conversational style. Unlike other, more obsolete kinds of search, NLP for real estate understands keywords, context, analyses the search intent, and can retrieve results based on these factors, which would be the most relevant.

Here’s an example of how AI search can enhance property search on real estate portals based on the latest AI for real estate developments by AscendixTech.

The user enters the query into an AI property search chat in a simple conversational manner. For instance, ‘Find me cosy apartments in Paris for a long term, in a quiet safe area, the price should be $40-70 per day, ability to check-in any time, non-smoking, I expect Instagram worthy apartments.’

Natural Language Search for Property Listings

The AI-powered chat (AI Completion model from OpenAI) automatically identifies the key requirements and keywords in the query, such as location, budget, desired amenities, and any additional preferences. It converts the user input to match the filtering options available in the system, and the AI Completion model suggests the search function with corresponding filters.

Except for identifying formal keywords like ‘Paris‘ (location), ‘long-term’ (duration), or ‘$40-70‘ (price), the system can understand and transform semantically similar phrases into filters. For example, the user request ‘with a possibility to cook’ will be transformed to the formal filtering criteria ‘kitchen,’ which will later be applied in the amenities field.

When the function is called, AI Search narrows down the number of matching properties by applying the filters. For the remaining properties, the hybrid AI property search – a combination of Vector and Full Text in Azure Cognitive Search – is performed.  If the user entered text that is not covered by the filters, it would be processed as a text query using AI Cognitive Search, meaning the semantic search NLP finds the closest common match to what the user asked for.

Due to this, both the properties containing the keywords from the text query and those with similar meanings are found. For example, if the user searches for ‘sleek contemporary aesthetics,’ the results will also include properties with ‘modern and minimalist design.’

Automatically Applied Filters in AI Property Search

After the main part of natural language search has been conducted, the search results are retrieved and ranked by relevance to the customer’s query. Real estate AI technology identifies the results that coincide with the search intent the most and shows them, starting from the most relevant and going to the least relevant ones or less interesting for the user.

As the results are ranked and reviewed, the user may make some adjustments, if they think of some other features needed. There is also the possibility to remove the previously set filters, for instance, to disregard the property prices, or add ‘cleaning‘ to desirable amenities. Whenever the user alters their search criteria, AI-powered chat uses not only the most recent input but the entire conversation history for a better context understanding and providing the best results.

Adjustment of Filters in Natural Language Search  To understand the context better, the chat saves the history of user queries and adjustments made to the initial request. Due to this, the semantic search LLM system can find ways to improve the search results and make them more relevant for a specific user within one dialogue in the chat. With the example of Ascendix AI property search, NLP for real estate agents improves and personalizes the results within a single search session, which means the end results are the most suitable to the user’s needs and desires, and if the person changes their mind about the property and wants to start from scratch, they can simply refresh the page and begin a whole new search.

How does Ascendix help Real Estate Marketplace Owners?

By adapting our services to your specific requirements, we design custom real estate software for individual marketplace owners looking to enhance their operational efficiency with the help of AI. Ascendix has a combination of real estate and AI expertise,our extensive expertise, industry experience, and reliability, we have garnered the trust of major real estate players such as JLLColliers, and Hanna Commercial, streamlining their business workflows effectively.

For real estate professionals, we specialize in integrating and customizing AI solutions within their existing real estate software infrastructure, meaning enhanced experience for customers. For those who already have a rental marketplace, Ascendix’s expertise in integration and development can ensure that AI natural language search elevates the customer experience on the platform and streamlines existing operations.

The NLP real estate technology allows users to search for properties using natural conversational language. Our team also included the map visualization to make sure the users are fully aware of where the most relevant properties are located. Customers get the best properties suiting their needs quickly and conveniently. We boost real estate marketplace with the help of a cutting-edge AI searching tool. The possibilities of natural language search enhance the customer experience on the rental platform and can help prospective tenants find the most relevant property tailored to their needs easier and faster.

With over 20-years of experience in the real estate industry and a dedicated focus on proptech development for 16-years, we bring unparalleled industry knowledge to the table. Our skilled team are professionals in software development and AI integration with a focus on the real estate industry’s needs and wants, which enables us to produce innovative and high-quality AI-powered solutions. Our global presence spans five offices, enabling seamless collaboration across continents.

To find out more please use this LINK

Does Generative AI mean the end for content creators?

Does Generative AI mean the end for content creators? Since ChatGPT burst onto the scene less than 18-months ago, that’s the question that marketers have been asking. Not only can Generative AI models produce copy, but they are now increasingly effective at creating images and videos. So, should companies use professional communicators or turn to AI for their marketing and copywriting needs?

I asked ChatGPT and experienced marketing professional Adrian Bishop whose work I have admired and endorsed for many years to discuss four crucial points about the future of AI and content creation. I also asked Adrian to tell us more about his marketing agency, Yellow Online Media, and whether he uses AI in the services he provides. In the following article machine goes toe to toe with human, we ask the same question, we get very different answers/outputs.

QCan AI replace content creators?

ChatGPT: Generative AI has the potential to augment the capabilities of content creators rather than replace them entirely. While AI can assist with tasks like generating ideas, providing inspiration, or even drafting initial content, it still lacks the human touch, creativity, and emotional intelligence that are essential for producing truly compelling and engaging content. Content creators can leverage AI as a tool to streamline workflows, enhance productivity, and unlock new creative possibilities, but their unique insights, perspectives, and storytelling abilities remain irreplaceable.

Adrian Bishop: AI is indeed an effective aid for copywriters, but it is not a complete replacement. ChatGPT and other generative AI models analyse patterns to find the best answer to the given prompt, but may struggle to generate original ideas or perspectives. They rapidly access data and generate copy, but do not have the creativity and nuances of skilled human writers. Of course, some companies are happy to use ChatGPT instead of hiring copywriters, but the results can lack depth, insight and creativity.

QWhat is AI best used for?

ChatGPT: A focus on higher-value tasks. As Generative AI takes on repetitive or time-consuming tasks in content creation, content creators can focus on higher-value activities that require human creativity, critical thinking, and emotional intelligence. This shift allows creators to devote more time and energy to activities like strategy development, audience engagement, and content optimization, ultimately leading to the production of higher-quality and more impactful content.

Adrian Bishop: This may be true, but for most writers, their primary skill is to write and edit rather than to plan, manage and organise. AI can be used to produce draft copy, but human writers should then take it and improve it. For instance, AI content can often be formulaic, and you will see similar phrasing repeated, while intros tend to lack creativity. 

This may be true, but for most writers, their primary skill is to write and edit rather than to plan, manage and organise. AI can be used to produce draft copy, but human writers should then take it and improve it. For instance, AI content can often be formulaic, and you will see similar phrasing repeated, while intros tend to lack creativity.

QDoes AI have a role in building collaborative partnerships?

ChatGPT: The future of content creation may involve collaborative partnerships between humans and AI, where creators work alongside intelligent algorithms to harness the strengths of both. By combining human ingenuity with AI-driven insights and automation, creators can unlock new levels of efficiency, innovation, and effectiveness in content creation. These partnerships empower creators to push the boundaries of creativity, experiment with new formats and mediums, and deliver content experiences that resonate deeply with audiences.

Adrian Bishop: This is essentially what we covered in the last point. AI with human editing produces better copy than AI content alone. Human input is certainly needed to inject a creative spark and check errors and inaccuracies.

Q Are there any ethical worries?

ChatGPT: As Generative AI becomes more prevalent in content creation, there are important ethical and regulatory considerations to address. Creators must navigate issues related to plagiarism, copyright infringement, bias, misinformation, and data privacy when using AI tools. It’s crucial to establish clear guidelines, standards, and best practices for the responsible use of AI in content creation and to prioritize transparency, accountability, and ethical integrity in all content production processes.

Adrian Bishop: Something we both agree on. There are already legal cases pending about potential copyright infringement concerning the material in language models used to train the AI models. Content generated by AI may contain misinformation, outdated details or even content that is wildly inappropriate that is based on wrong assumptions. For instance, when looking for ideas for real estate clients, AI has often brought up information about the wrong developer, incorrect listings and services that are not offered. While Generative AI presents both opportunities and challenges for content creators, it doesn’t spell the end for their craft.

Does Yellow Online Media use AI?

Over the last year, I (Adrian Bishop) have written around one million words for clients of my communications agency, Yellow Online Media, in blogs, social media posts, newsletters, web content and other marketing material, says Adrian Bishop. I am a former award-winning UK journalist and editor, who now lives and works in Canada on behalf of large and small clients around the world, including residential and commercial property companies.

Those words are checked by the Grammarly AI-assisted writing tool. Who can resist an app that declared last week, “You’ve achieved grammar greatness!?”

That’s a lot of content – and many clients ask whether Yellow Online Media uses generative AI to assist us in other ways. The answer is yes, but judiciously. And we are not alone. The 2024 Benchmark Report from the Influencer Marketing Hub suggests that 61% of communication professionals have used AI for marketing and 44% for content production.

ChatGPT, Copilot, Bard and other Generative AI brands are useful for producing subject ideas, outlines, structure and sample copy for comparison and inspiration. They can help improve grammar, phrasing and syntax and are helpful in summarising long, complex text.

For all their benefits, they lack human understanding and a personal, distinctive writing style. Generative AI copy can be formulaic, contain factual errors and may not be up-to-date. It also needs careful prompting to produce the right result. But when correctly employed by an experienced writer, Generative AI can provide new ideas, freshen and strengthen content, and improve efficiency and accuracy.

If you need support to achieve your marketing goals, Yellow Online Media – with a little help from Generative AI – can provide compelling copy and save you time and money. For content, news, blogs, social media posts, newsletters and more, email’

Andrew Stanton’s PROPTECH-X ‘Proptech & Property News’ in association with Estate Agent Networking & News Now publications. #proptech #property #realestate #digitaltransformation #startups

Visited 1 times, 1 visit(s) today

Andrew Stanton CEO of Proptech-PR, a consultancy for Founders of Proptechs looking to grow and exit, using his influence from decades of industry experience. Separately a consultant to some of the biggest names in global real estate, advising on sales and acquisitions, market positioning, and operations. Founder and editor of Proptech-X Proptech & Property News, where his insights, connections and detailed analysis and commentary on proptech and real estate are second to none having met 1,000 Proptech founders, critiqued 400 decks and had 130 Proptechs as clients. With an audience of 100K followers & readers, he is best known as being a 'Proptech Realestate Influencer' both shaping and reporting on the digital transformation of the industry.