DE202023106049U1 - A machine learning based property price prediction system - Google Patents

Abstract

A machine learning-based real estate price prediction system, comprising:a storage unit that stores a data set containing listing data from various public sources, the data set containing a variety of information relating to a particular residential property;a pre-processing module that so is configured to create feature vectors by taking inputs from the storage module, the pre-processing module using an encoding processor to perform one-hot encoding to create a categorical variable for each residential property; a main processing unit into which a data set is based trained machine learning model and artificial neural networks embedded with different hyperparameters capable of predicting the price of a residential property, the output predicted price being subject to the input parameters relating to the corresponding residential property; andan output processing module comprising a user interface configured to provide the predicted output from the main processing unit.

Description

FIELD OF THE INVENTION

The present disclosure relates to the field of real estate technology, particularly to a machine learning-based system for predicting real estate prices. In particular, the present disclosure relates to a machine learning-based system for solving the problem of property price prediction in classified ads.

BACKGROUND OF THE INVENTION

The next big thing shaking up the real estate industry is real estate technology (PropTech). PropTech advocates the use of technology to facilitate the management and operation of real estate assets. Assets can be either cities or buildings. PropTech focuses on both technological and behavioral change among those working in the real estate sector, including its customers. It can be viewed as part of the digital transformation of the real estate industry. In addition, proptech can provide additional functions such as greater transparency. PropTech also includes big data, data analytics, machine learning, blockchain and sensors.

There are numerous property classification websites in India that offer properties for sale, purchase or rent. However, there is a lot of variation in apartment prices across these websites, and there are some cases where identical apartments are priced differently, leading to major inconsistencies. Customers may occasionally believe that the price of a particular apartment on the listing is inflated, but there is no way to verify this. Since most consumers, especially in India, find transaction prices quite high, addressing this issue will benefit both customers and the real estate industry in the long run.

Correct and justified real estate prices can restore a high level of transparency and trust to the real estate industry.

In order to provide a solution to the above problem of proactive pricing of houses listed in classified ads on websites in the Indian real estate market, machine learning can be used and a system should be developed that can predict the price of a house.

From the above discussion, it is clear that there is a need for a machine learning based property price prediction system.

SUMMARY OF THE INVENTION

The present disclosure relates to a machine learning-based real estate price prediction system. This invention provides a system that uses machine learning and artificial neural networks to predict the prices of an apartment based on related parameters, the system aiming to solve the problem of house price prediction in classified ads. Machine learning algorithms such as random forest, gradient boosting and artificial neural networks are implemented on real datasets and then evaluation metrics are used to compare the performance of different models of the proposed system based on prediction accuracy.

The present disclosure aims to provide a machine learning-based real estate price prediction system. The system includes: a storage device that stores a record containing listing data from various public sources, the record containing a variety of information relating to a particular residential property; a preprocessing module configured to create feature vectors by taking inputs from the storage module, the preprocessing module using an encoding processor to perform one-hot encoding to create a categorical variable for each residential property; a main processing unit in which a machine learning model trained on the datasets and artificial neural networks with different hyperparameters are embedded, capable of predicting the price of a residential property, where the output predicted price depends on the input parameters relating to the corresponding residential property relate ; and an output processing module including a user interface configured to provide the predicted output from the main processing unit. The machine learning-based system also includes: a communication module that uses an internal data bus to provide uninterrupted communication between components of the system; and a power supply unit to provide power to the system so that the components of the system can operate continuously.

An objective of the present disclosure is to provide a machine learning-based system for predicting real estate prices.

Another aim of the present disclosure is to solve the problem of property price prediction in classified ads.

Another objective of the present disclosure is to use machine learning algorithms to develop a system that can predict the price of the house based on certain input characteristics.

Another objective of the present disclosure is to develop a system that can be applied to the Indian real estate market for large companies.

In order to further illustrate the advantages and features of the present disclosure, a more detailed description of the invention will be made with reference to specific embodiments thereof shown in the accompanying drawings. It is understood that these drawings represent only typical embodiments of the invention and are therefore not to be viewed as limiting its scope. The invention is described and explained in more detail and in greater detail with reference to the accompanying drawings.

BRIEF DESCRIPTION OF THE FIGURES

• 1 zeigt ein Blockdiagramm eines auf maschinellem Lernen basierenden Systems zur Vorhersage von Immobilienpreisen.
• 2 veranschaulicht den Arbeitsrahmen des vorgeschlagenen, auf maschinellem Lernen basierenden Systems zur Vorhersage von Immobilienpreisen.
• 3 veranschaulicht eine Tabelle, die die Ergebnisse des Vergleichs zwischen verschiedenen Modellen des vorgeschlagenen Systems gemäß einer Ausführungsform der vorliegenden Offenbarung zeigt.

These and other features, aspects and advantages of the present disclosure will be better understood when the following detailed description is read with reference to the accompanying drawings, in which like reference numerals represent like parts throughout the drawings, in which:

• 1 shows a block diagram of a machine learning-based property price prediction system.
• 2 illustrates the working framework of the proposed machine learning-based real estate price prediction system.
• 3 illustrates a table showing the results of comparison between various models of the proposed system according to an embodiment of the present disclosure.

Additionally, experienced craftsmen will recognize that elements in the drawings are presented for convenience and may not necessarily have been drawn to scale. For example, the flowcharts illustrate the method through key steps that help improve understanding of aspects of the present disclosure. Additionally, in view of the construction of the device, one or more components of the device may have been represented in the drawings by conventional symbols, and the drawings may show only the specific details relevant to understanding the embodiments of the present disclosure around the drawings not to be obscured by details that would be readily apparent to one of ordinary skill in the art using the description herein.

DETAILED DESCRIPTION:

In order to promote understanding of the principles of the invention, reference will now be made to the embodiment shown in the drawings and specific language will be used to describe the same. It is to be understood, however, that this is not intended to limit the scope of the invention, since changes and further modifications to the system illustrated and further applications of the principles of the invention set forth therein are contemplated as would normally occur to one skilled in the art Technology to which the invention relates.

Those skilled in the art will understand that the foregoing general description and the following detailed description are exemplary and illustrative of the invention and are not intended to limit the same.

References in this specification to “an aspect,” “another aspect,” or similar language mean that a particular feature, structure, or characteristic described in connection with the embodiment is included in at least one embodiment of the present disclosure is included. Therefore, the phrases “in one embodiment,” “in another embodiment,” and similar phrases in this specification may, but not necessarily, refer to the same embodiment.

The terms “includes,” “comprising,” or other variations thereof are intended to cover non-exclusive inclusion, such that a process or method that includes a list of steps not only includes those steps, but may include other steps not specifically listed or following this inherent in the process or method. Likewise, one or more devices or subsystems or elements or structures or components preceded by “comprises...a” do not exclude existence without further qualification other devices or other subsystems or other elements or other structures from other components or additional devices or additional subsystems or additional elements or additional structures or additional components.

Unless otherwise defined, all technical and scientific terms used herein have the same meaning as generally understood by one of ordinary skill in the art to which this invention pertains. The system, methods and examples provided herein are for illustrative purposes only and are not intended to be limiting.

Embodiments of the present disclosure are described in detail below with reference to the accompanying drawings.

The functional units described in this specification are identified as devices. A device may be implemented in programmable hardware devices such as processors, digital signal processors, central processing units, field programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems, or the like. The devices can also be implemented in software for execution by different types of processors. An identified device may contain executable code and, for example, include one or more physical or logical blocks of computer instructions, which may be organized, for example, as an object, procedure, function, or other construct. However, the executable file of an identified device does not have to be physically located together, but may consist of different instructions stored in different locations, which, when logically assembled, form the device and fulfill the stated purpose of the device.

In fact, a device or module's executable code could be a single instruction or multiple instructions, and even distributed across several different code segments, between different applications and across multiple storage devices. Similarly, operational data may be identified and represented herein within the device and may be embodied in any suitable form and organized into any suitable type of data structure. The operational data may be collected as a single data set or distributed across various locations, including various storage devices, and may exist, at least in part, as electronic signals in a system or network.

References in this specification to “a selected embodiment,” “an embodiment,” or “an embodiment” mean that a particular feature, structure, or feature described in connection with the embodiment is disclosed in at least one embodiment of the Item is included. Therefore, the expressions “a selected embodiment,” “in one embodiment,” or “in one embodiment” used elsewhere in this specification do not necessarily refer to the same embodiment.

Additionally, the features, structures, or properties described may be combined in any suitable manner in one or more embodiments. In the following description, numerous specific details are provided to provide a thorough understanding of embodiments of the disclosed subject matter. However, one skilled in the art will recognize that the disclosed subject matter may be practiced without one or more of the specific details or with other methods, components, materials, etc. In other cases, well-known structures, materials, or processes may not be shown or described in detail so as not to obscure aspects of the subject matter disclosed.

According to exemplary embodiments, the disclosed computer programs or modules may be executed in many exemplary ways, for example, as an application residing in a device's memory or as a hosted application executing on and communicating with a server via a device application or browser Set of standard protocols such as TCP/IP, HTTP, XML, SOAP, REST, JSON and other sufficient protocols. The disclosed computer programs may be written in exemplary programming languages that are executed from the device's memory or from a hosted server, such as BASIC, COBOL, C, C++, Java, Pascal, or scripting languages such as JavaScript, Python, Ruby, PHP, Perl or other suitable programming languages.

Some of the disclosed embodiments involve or otherwise involve data transmission over a network, such as the transmission of various inputs or files over the network. The network may include, for example, one or more of the following elements: Internet, Wide Area Networks (WANs), Local Area Networks (LANs), analog or digital wired and wireless telephone networks e.g. B. a PSTN, Integrated Services Digital Network (ISDN), a cellular network and Digital Subscriber Line (xDSL), radio, television, cable, satellite and / or other transmission or tunneling mechanisms for data transmission. The network may include multiple networks or subnetworks, each of which may include, for example, a wired or wireless data path. The network may include a circuit-switched voice network, a packet-switched data network, or any other network capable of transmitting electronic communications. The network may include, for example, networks based on Internet Protocol (IP) or Asynchronous Transfer Mode (ATM), and may support voice using, for example, VoIP, Voice over ATM, or other comparable protocols used for voice data communications. In one implementation, the network includes a cellular network configured to enable the exchange of text or SMS messages.

Examples of the network include a Personal Area Network (PAN), a Storage Area Network (SAN), a Home Area Network (HAN), a Campus Area Network (CAN) and a Local Area Network (LAN), a Wide Area Network (WAN), a Metropolitan Area Network (MAN), a Virtual Private Network (VPN), an Enterprise Private Network (EPN), Internet, a Global Area Network (GAN) and so on.

1 shows a block diagram of a machine learning-based system (100) for predicting real estate prices. The system (100) includes a storage unit (102) that stores a data set (102a) containing listing data from various public sources, the data set (102a) containing a variety of information relating to a particular residential property.

In one embodiment, a pre-processing module (104) is configured to create feature vectors by taking inputs from the storage module, the pre-processing module (104) using a perfumed one-hot encoding encoding processor (104a) to a categorical variable for every residential property.

In one embodiment, a main processing unit (106) is embedded with a machine learning model trained on the data sets and artificial neural networks with different hyperparameters capable of predicting the price of a residential property, the predicted output price being subject to the input parameters relate to the corresponding residential property.

In one embodiment, an output processing module (108) includes a user interface (108a) configured to provide the predicted output from the main processing unit (106).

In one embodiment, the storage unit (102) uses a non-volatile memory (102b) to store the data.

In one embodiment, the data set (102a) contains information about the residential properties, and this information includes name, region, apartment type (2BHK, 3BHK and more), built-up area of the apartment, carpet area, number of bedrooms & bathrooms, price of the apartment, parking facilities ( yes/no), directional orientation listed by (agent/individual), facility status (fully furnished/partially furnished/unfurnished), amenities (gym, swimming pool, Wi-Fi, 24 hour power backup, etc.) and other information.

In one embodiment, the preprocessing module (104) comprises a volatile memory (104b) in which created feature vectors that correspond to a specific residential property are stored until the final prediction.

In one embodiment, the main processing unit (106) includes: using machine learning algorithms to perform regression and prediction tasks; and using an artificial neural network with various hyperparameters and using an activation function to learn non-linear relationships between the characteristics of a residential property and its price to enable accurate prediction of the price of the residential property.

In one embodiment, the output processing module (108) uses a user interface (108a), accepts input from the main processing unit, and displays the predicted price of the house using a physical display (108b).

In one embodiment, the machine learning-based system (100) further includes a communications module (110) that uses an internal data bus to provide uninterrupted communication between components of the system.

In one embodiment, the system (100) also includes a power supply unit (112) to provide power to the system so that the components of the system can operate continuously.

In one embodiment, the storage unit (102), the pre-processing module (104), the main processing unit (106), the output processing unit (108), the communication module (110) and the power supply unit (112) may be in programmable hardware devices such as processors, digital signal processors, central processing units , field programmable gate arrays, programmable array logic, programmable logic devices, cloud processing systems or the like.

Focusing on the Indian real estate industry, this invention provides machine learning based software to solve the problem of house price prediction in classified ads. To predict real estate prices using a real-world dataset, the proposed system uses advanced machine learning algorithms such as random forests, gradient boosting, and artificial neural networks. The different modules produced are then compared with each other to evaluate the performance of each model and determine which model has the highest prediction accuracy. The business benefit of this system is that classified websites can directly use it to predict prices of new properties to be listed by using some input variables and predict the correct and justified price, thereby avoiding taking price inputs from customers and errors will be prevented from creeping into the system.

2 illustrates the working framework of the proposed machine learning-based real estate price prediction system.

The invention attempts to address the problem of accurately predicting the cost of houses in Bengaluru based on nine characteristics including the type of area, its availability, its price, its size, its society, its total square footage, and the number of bathrooms and beds. These mentioned features are stored in a data set that is fed into the machine learning algorithms as input for prediction.

In this invention, the publicly available data is taken from websites, which then compiles the listing data from various publicly available sources, with the total observation in the data set being 66.

The target variable in the regression problem is price, and the independent variables are the target variable, number of bedrooms, number of bathrooms, built-up area, carpet area, furnishing condition, floor type, orientation, apartment type, region and equipment. Facilities are subjected to one-hot coding, where categorical variables are created for each facility. For example, the feature vector for Apartment 1, with a gym, pool, and WiFi but no cafeteria, would be [1 1 1 0], while the feature vector for Apartment 2, with a gym, pool, WiFi, and cafeteria, would be [1 0 0 0]. In total there are 56 independent variables.

Next, sophisticated machine learning techniques such as gradient boosting and random forests are used. The Random Forest (RF) uses ntrees = 5000 and Gradient Boosting (GBM) uses ntrees = 10000 and a learning rate = 0.01. In addition, the system uses artificial neural networks with various hyperparameters. To give an example, the ANN1 neural network has two hidden layers and 100 hidden nodes and uses two hidden layers. In ANN2, 3 hidden layers with 100 hidden nodes each are used and finally in ANN3, 3 hidden layers with 200 hidden nodes each are used. “Rectifier” is the activation function used. Mean percent error and mean percent error are the evaluation metrics used to compare the different techniques. The median was chosen because it is considered a reliable measure that is not influenced by outliers.

3 illustrates a table showing the results of comparison between various models of the proposed system according to an embodiment of the present disclosure.

Using the table in It can be seen that RF-based machine learning, i.e. Random Forest, performs best in terms of prediction accuracy. When evaluating the variable importance for the RF approach, it can be found that furnishing status, carpet area, built-up area, dwelling type, region, floor type, and number of bathrooms and bedrooms are the most important variables.

The drawings and the description above provide examples of embodiments. Those skilled in the art will recognize that one or more of the elements described may well be combined into a single functional element can. Alternatively, certain elements can be divided into several functional elements. Elements of one embodiment may be added to another embodiment. For example, the orders of the processes described herein may be changed and are not limited to the manner described herein. Additionally, the actions of a flowchart do not have to be implemented in the order shown; Not all actions necessarily have to be carried out. Even those actions that are not dependent on other actions can be carried out in parallel with the other actions. The scope of the embodiments is in no way limited by these specific examples. Numerous variations, whether explicitly stated in the specification or not, such as: B. Differences in structure, dimensions and material use are possible. The scope of the embodiments is at least as broad as indicated by the following claims.

Advantages, other benefits, and solutions to problems have been described above with respect to specific embodiments. However, the advantages, benefits, solutions to problems and any components that may cause a benefit, advantage or solution to occur or become more pronounced should not be construed as a critical, necessary or essential function or component of any or all of the claims.

CREDENTIALS

100

A machine learning based house price prediction system

102

Storage unit

102a

A data set

102b

Non-volatile memory

104

Preprocessing module

104a

Encoding processor

104b

Volatile memory

106

Main processing unit

108

Output processing module

108a

user interface

110

Communication module

112

power adapter

202

Preparation of feature vectors

204

Input parameters

206

Machine learning models to predict house price

208

Random Forest (RF)

210

Gradient Boost (GBM)

212

Artificial Neural Networks (ANN)

214

Predicted output displayed in the user interface

Claims (8)

A machine learning based property price prediction system consisting of: a storage device that stores a record containing listing data from various public sources, the record containing a variety of information relating to a particular residential property; a preprocessing module configured to create feature vectors by taking inputs from the storage module, the preprocessing module using an encoding processor to perform one-hot encoding to create a categorical variable for each residential property; a main processing unit in which a machine learning model trained on the data sets and artificial neural networks with different hyperparameters are embedded, capable of predicting the price of a residential property, the output predicted price being subject to the input parameters relating to the corresponding residential property ; and an output processing module comprising a user interface configured to provide the predicted output from the main processing unit. System after Claim 1 , where the storage unit uses non-volatile memory to store the data. System after Claim 1 , where the dataset contains information about the residential properties and this information includes name, region, apartment type (2BHK, 3BHK and more), built-up area of the apartment, carpet area and number of bedrooms and bathrooms, price of the apartment, parking availability (yes/no) , Directional Orientation, Listed by (Agent/Individual), Facility Status (Fully Furnished/Partially Furnished/Unfurnished), Amenities (Gym, Swimming Pool, WiFi) . , 24-hour emergency power supply, etc.) and other information. System after Claim 1 , wherein the pre-processing module comprises a volatile memory in which created feature vectors corresponding to a particular residential property are stored until the final prediction. System after Claim 1 , wherein the main processing unit includes: using machine learning algorithms to perform regression and prediction tasks; and using an artificial neural network with various hyperparameters and using an activation function to learn non-linear relationships between the characteristics of a residential property and its price to enable accurate prediction of the price of the residential property. System after Claim 1 , wherein the output processing module uses a user interface, accepts input from the main processing unit, and displays the predicted price of the house using a physical display. System after Claim 1 , further comprising a communication module that uses an internal data bus to provide uninterrupted communication between components of the system. System after Claim 1 , further comprising a power supply unit for supplying power to the system so that the components of the system can operate continuously.

Images