DESC:4. DESCRIPTION
Technical Field of the Invention

The present invention relates to the field of computer-implemented systems and methods for evaluating and facilitating rental transactions. More specifically, the invention operates within the domain of real estate technology, leveraging digital platforms to assess the suitability of tenants for rental properties and to provide landlords with valuable insights into tenant behaviour and history.

Background of the Invention

Tenant selection plays a critical role in property management, directly influencing financial outcomes, property maintenance, and community harmony. Traditionally, landlords and Resident Welfare Associations (RWAs) rely on manual and fragmented processes to verify the background of prospective tenants. These include basic document submissions, in-person interviews, police verification, and references from previous landlords. While these methods provide some level of screening, they lack standardization, scalability, and real-time data validation, making them susceptible to bias, manipulation, and human error.

Conventional tenant verification systems, including legacy property management software, generally focus on storing tenant profiles and payment logs but fall short in providing predictive analytics or behavioral insights. Most of these systems do not incorporate machine learning models or advanced scoring algorithms to evaluate a tenant’s risk potential. Moreover, they lack integration with external databases such as regulatory agencies, credit bureaus, and police records, which are crucial for a holistic assessment. Prior art methods also fail to adapt to property-specific or community-specific requirements, offering only rigid, one-size-fits-all screening templates that are neither customizable nor dynamic.

Another disadvantage of existing systems is the absence of secure, automated agreement execution and digital access provisioning. Lease agreements continue to be signed manually, often resulting in delays, legal non-compliance, and administrative overhead. Additionally, once a tenant is approved, there is no standardized system for granting secure access to gated communities or housing complexes. This creates operational friction and exposes residential societies to unauthorized entry risks.

The rapid growth of urban housing, the rise of co-living spaces, and increased mobility of tenants have intensified the need for a unified, intelligent, and secure tenant screening system. There is a dire need for a technology-driven platform that not only scores tenants based on quantitative and qualitative parameters but also automates approval workflows, digitizes agreement execution, and ensures secure property access. The need is further accentuated in high-density residential areas where screening hundreds of tenants manually is infeasible, and the consequences of poor tenant selection can be legally and financially damaging.

Objects of the Invention

An object of the present invention is to provide a technically robust and intelligent tenant scoring system that enables landlords and Resident Welfare Associations (RWAs) to evaluate tenants using objective, real-time, and data-driven methods. The system is designed to overcome the limitations of conventional verification processes by integrating various data sources and applying advanced analytics to generate a comprehensive tenant reliability score.

Another object of the invention is to offer a modular scoring architecture that allows dynamic selection and customization of evaluation parameters, such as timely rental payments, maintenance compliance, damage history, and behavioral patterns. This flexibility enables landlords to tailor the scoring model to their specific property type or risk tolerance, thereby improving the precision and relevance of tenant assessments.

A further object of the invention is to incorporate machine learning algorithms within the scoring module to analyze historical data and identify high-risk behavioral patterns in prospective tenants. By leveraging predictive modeling techniques, the system can generate risk classifications and behavioral trend forecasts that enhance the decision-making capabilities of landlords and RWAs.

Yet another object of the invention is to provide an agreement automation module that digitally facilitates the secure signing of tripartite rental agreements among landlords, tenants, and RWAs. The system ensures non-repudiation, tamper-resistance, and auditability of agreements by using blockchain-based time stamping and digital authentication mechanisms, thus significantly reducing manual errors and delays.

Another object of the invention is to provide an intelligent community access control mechanism that generates digitally verifiable, QR-coded access credentials for approved tenants. These credentials are transmitted to IoT-enabled smart gate systems, enabling time-bound and secure property entry without requiring physical intervention, thereby streamlining move-in procedures and enhancing community safety.

A still further object of the invention is to enable seamless user interaction through web and mobile interfaces, offering intuitive dashboards, real-time score visualization, agreement status tracking, and feedback modules for all stakeholders. This unified interface simplifies operational workflows and ensures transparency across all stages of tenant onboarding and management.

The invention also aims to ensure end-to-end data security and regulatory compliance by employing encryption, role-based access controls, and secure communication protocols across all system modules. This reinforces trust in the system and ensures the confidentiality and integrity of sensitive tenant information.

Through these and other objects, the present invention provides a holistic, scalable, and intelligent platform for modern rental ecosystems, especially suited for high-density residential complexes, gated communities, and professionally managed rental portfolios.
Brief Summary of the Invention

Aspects of the present invention relate to a tenant scoring system that provides a technologically advanced and automated framework for evaluating the suitability and reliability of tenants based on multiple behavioural, financial, and regulatory factors. The invention leverages modular software components, real-time data acquisition, artificial intelligence, and secure digital workflows to offer a comprehensive solution for landlords and Resident Welfare Associations (RWAs) in managing tenant onboarding, scoring, and access provisioning processes.

One aspect of the present invention provides a user interface module that facilitates interaction between system users, including landlords, tenants, and RWAs, allowing seamless input and visualization of tenant-related data, scores, and agreements. Another aspect of the invention concerns a data collection module configured to aggregate structured and unstructured data from various sources such as rental agencies, property managers, credit bureaus, and regulatory bodies via secure API channels.

A further aspect of the invention includes a parameter identification and scoring engine that dynamically selects tenant evaluation criteria and applies statistical and machine learning models to compute reliability scores. These scores are normalized and aggregated using defined weight profiles, taking into account the frequency, severity, and recency of tenant behaviour. The use of AI in behavioural risk prediction distinguishes the system from conventional scoring methods, enabling predictive insights that aid in informed tenant selection.

Additional aspects of the invention include an agreement automation module that facilitates secure, sequential digital signing of tripartite lease agreements using blockchain-enabled timestamping and authentication. The system further comprises a community access control module, which upon successful agreement execution, issues QR-coded, time-bound access passes integrated with IoT-enabled gate systems to ensure secure and automated property access.

Through these integrated modules, the invention not only standardizes and streamlines tenant evaluation but also enhances trust, security, and operational efficiency in rental property management environments. The invention may be particularly beneficial in large residential communities, gated societies, and commercial rental properties where tenant verification and access control are critical.

Brief Description of the Drawings

The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate various exemplary embodiments of the invention and together with the detailed description serve to explain the principles of the invention.

FIG. 1 illustrates a system architecture diagram representing the interconnected functional modules of the tenant scoring system.

FIG. 2 illustrates a method flow diagram showing the step-by-step process of evaluating tenant behaviour.

FIG. 3A illustrates the initial step in the agreement workflow, where the system generates a tripartite agreement link upon tenant approval and sends it to the landlord via a secure digital communication channel.

FIG. 3B illustrates the process where the landlord reviews the agreement and digitally signs it, which is then verified and updated by the system.

FIG. 3C illustrates the tenant signature phase, where the tenant authenticates and signs the agreement using the same secure digital interface.

FIG. 3D illustrates the final stage of agreement execution wherein the Resident Welfare Association (RWA) signs the agreement, completing the digital signature process and triggering finalization and storage.

FIG. 3E illustrates the system's automated generation of QR-coded, time-bound digital access credentials for the tenant and transmission to the IoT-enabled community gate system for secure entry.

FIG. 4A illustrates the core architecture of the tenant scoring system, covering the initial stages of tenant onboarding, beginning with the registration process where the landlord and tenant submit their respective property and identity details.

FIG. 4B illustrates the reporting and decision-making workflow beginning with the report generation module, which compiles results from the completed verifications and scoring algorithms into structured reports.

FIG. 4C illustrates the system’s legally compliant agreement workflow and access provisioning process.

FIG. 4D provides a system-level interaction overview, mapping the roles of key system stakeholders including the landlord, tenant, and Resident Welfare Association (RWA).

Detailed Description of the Invention

In accordance with exemplary embodiments of the present invention, a tenant scoring system is provided to assist landlords and Resident Welfare Associations (RWAs) in making data-driven decisions when assessing prospective tenants. The system functions as an integrated software platform comprising multiple interacting modules designed to collect, process, analyze, and act upon tenant-related data.

In one embodiment, the system provides a user interface that enables various stakeholders, including landlords, tenants, and RWAs, to interact with the platform. The interface is designed for intuitive operation and supports multiple access types based on user roles. Through the interface, landlords can input tenant data, review score reports, and approve or reject candidates. Tenants may also be allowed to view their own scores, raise disputes, and complete digital agreements. The interface may be deployed via web browsers or mobile applications with secure login protocols.

The system includes a data collection module capable of retrieving tenant data from diverse sources. These sources may include rental agencies, property management software, credit bureaus, police verification records, and historical landlord feedback. The module is configured to normalize data from different formats and consolidate it for use in the scoring engine. This ensures comprehensive and accurate profiling of tenants, enabling deeper behavioral insights.

Once data is collected, the parameter identification module identifies relevant evaluation criteria based on predefined settings or user preferences. These criteria may include but are not limited to timely rent payments, frequency of complaints from neighbors, property damage incidents, compliance with community rules, and historical dispute resolution behavior. The system may dynamically adjust which parameters are emphasized based on the property type or user-defined configurations.

A weighting module then assigns different levels of significance to each identified parameter. These weights may be fixed or customizable, allowing landlords and RWAs to fine-tune the scoring logic based on risk appetite, property value, or community policy. For instance, in high-value properties, the weight for timely rent payment may be higher, while for co-living environments, social behavior and noise complaints may carry more weight.

Following parameter weighting, a scoring module processes the input data to generate individual scores for each parameter. The scoring logic may consider frequency, severity, and recency of events to yield a fair and reflective assessment. In advanced embodiments, this module may include a machine learning model that analyzes historical data to identify patterns associated with high-risk or high-performing tenants. These predictive capabilities enable landlords to anticipate potential issues before leasing decisions are made.

A normalization and aggregation module then converts all parameter scores to a uniform scale and aggregates them using the weighted formula to produce a unified tenant reliability score. This score serves as a quantified reflection of the tenant’s overall suitability, with the ability to benchmark performance against peer groups or community standards.

The platform further includes a report generation module that creates detailed tenant evaluation reports. These reports present the breakdown of parameter-wise scores, the total tenant score, predictive risk classification, and optional recommendations. They are automatically formatted and made available for secure download or sharing through the user interface.
To facilitate consensus between the landlord and the RWA, a collaborative decision interface enables both parties to review score reports, leave comments, and jointly approve or reject tenant applications. This feature helps maintain transparency and accountability in the tenant selection process.

Upon approval, the agreement automation module initiates the creation of a tripartite lease agreement digitally binding the landlord, tenant, and RWA. The agreement is automatically populated using stored data and routed sequentially for digital signatures. Each party signs via a secure link, and the system tracks the signing status in real time. In some embodiments, blockchain technology may be used to create tamper-proof audit logs of the agreement.

After execution of the lease agreement, the system automatically generates community access credentials. These credentials may include a time-bound QR code or digital token that allows the tenant to access the premises securely. The access control mechanism may be integrated with smart gates or IoT-enabled security systems that validate the QR code in real-time before allowing entry.

In summary, the exemplary embodiments of the present invention disclose a modular, data-driven tenant scoring system that streamlines the entire tenant onboarding lifecycle from evaluation and decision-making to agreement execution and access provisioning. The invention provides technical solutions to long-standing issues in rental housing, such as subjectivity in tenant assessment, inefficiencies in documentation, and lack of secure entry control. By introducing automation, analytics, and secure workflows, the system substantially improves reliability, transparency, and operational efficiency for landlords, tenants, and housing communities alike.

Referring to FIG. 1, the tenant scoring system is architected as a modular digital platform comprising multiple subsystems that operate in a sequential and integrated manner. The system begins with a User Interface Module (102), which acts as the central access layer for all stakeholders, including landlords, tenants, and Resident Welfare Associations (RWAs). The user interface is designed to support role-based access and provides intuitive dashboards for data input, score viewing, agreement tracking, and feedback exchange.

The Data Collection Module (104) functions as the ingestion layer of the platform. It collects tenant-related data from heterogeneous sources such as property management systems, rental agency records, credit bureaus, and regulatory compliance databases. The module supports API-based data retrieval and structured form uploads, ensuring secure and authenticated integration with external entities. The collected data includes transactional logs, historical complaints, maintenance records, lease compliance indicators, and financial behaviour metrics.

Once the data is collected, it is passed to the Parameter Identification Module (106), which dynamically selects relevant evaluation criteria. These may include, for example, the number of late payments, frequency of noise complaints, damage incidents, participation in community activities, or positive feedback from previous landlords. FIG. 2 illustrates this evaluation process as part of a sequential method that captures, filters, and prepares tenant data for scoring.

The Weighting Module (108) receives the identified parameters and applies configurable importance levels to each based on landlord or community policies. For instance, in a high-end residential apartment, timely rent payments may be given more weight than social behaviour, whereas in a co-living space, community engagement may be emphasized. These weights are applied during score computation to balance the scoring outcome based on the priorities of the property owner or governing body.

Next, the Scoring Module (110) executes the core analytical logic. The system can operate using either rule-based scoring logic or an embedded machine learning engine. In one embodiment, a random forest classifier is trained on labelled historical tenant data to learn patterns indicative of undesirable or desirable behaviour. The algorithm uses parameters such as the recency, frequency, and severity of tenant actions to compute intermediate scores. A simplified version of the scoring logic is represented as:
score = S (normalized_parameter_i × weight_i)

Where each parameter is normalized to a common scale using techniques such as Z-score or min-max scaling, and the corresponding weight is applied before aggregation.

The Normalization and Aggregation Module (112) standardizes the scores to avoid bias from data scale disparities and aggregates them into a unified tenant reliability score. FIG. 2 reflects the normalized score calculation and the output generation flow.

After the tenant score is generated, the Report Generation Module (114) compiles a structured and tamper-proof evaluation report. This report includes the parameter-wise score breakdown, overall tenant score, risk classification label (e.g., low risk, moderate risk, high risk), and a confidence index. The Presentation Module (116) ensures that these reports are delivered to landlords and RWAs through the user dashboard with optional export formats such as PDF or CSV.

For multi-party decision-making, the Collaborative Decision Interface (118) facilitates consensus building between landlords and RWAs. Stakeholders can comment on reports, approve or reject applicants, and store approval records in a secure log. FIG. 4B illustrates the integration between report generation, decision-making, and stakeholder review loops.

Upon tenant approval, the Agreement Automation Module (120) initiates the generation of a legally compliant digital lease agreement. As shown in FIG. 3A to FIG. 3D, this agreement progresses through a sequential signing process beginning with the landlord, followed by the tenant, and finally the RWA. Each party receives a secure link via SMS or messaging platforms and digitally signs the document. Blockchain-based hashing may be used to preserve the integrity of the agreement, and all actions are timestamped and stored in the Agreement Database.

Following execution of the agreement, the Community Access Control Module (122) automatically issues a QR-coded move-in pass to the tenant. This access credential is time-bound and revocable, and it integrates with smart gate systems or IoT-based access terminals at the residential property. FIG. 3E depicts this process where successful agreement completion results in seamless access provisioning to the tenant.

The system is further supported by the layered architecture illustrated in FIG. 4A to FIG. 4D. These figures detail the full workflow from registration and verification to digital signature management and gate-level access provisioning. FIG. 4A shows the upstream modules involving data collection and verification. FIG. 4B captures the scoring, reporting, and decision logic. FIG. 4C illustrates the downstream workflow of agreement finalization and access provisioning. FIG. 4D consolidates these components with the roles of external entities—landlord, tenant, and RWA—interfacing via secure protocols.

The best mode of operation includes pre-configured parameter templates for various property types, automated machine learning model updates based on retraining cycles, and integrated monitoring dashboards for real-time alerts. For instance, if a tenant’s score drops below a configurable threshold post-move-in (e.g., due to delayed payments or recorded complaints), the system can trigger alerts or re-evaluation workflows.

These exemplary embodiments offer a comprehensive, secure, and intelligent solution to the multifaceted challenges of tenant evaluation, digital leasing, and controlled community access.
The tenant scoring system (100) is composed of multiple interconnected technical modules working in sequence to digitize and automate tenant evaluation, agreement execution, and access control. Referring to FIG. 1, the system comprises a User Interface Module (102) which allows tenants, landlords, and Resident Welfare Associations (RWAs) to interact with the system. The interface enables role-based operations including tenant data input, report access, document signing, and credential issuance.

The Data Collection Module (104) collects tenant-related data from multiple sources including property management systems, credit bureaus, and government databases. This data includes rental history, regulatory compliance, maintenance records, and community feedback. The data is further processed in the Parameter Identification Module (106) which identifies relevant parameters such as payment history, complaint frequency, damage incidents, and social behaviour.

The Weighting Module (108) allows configuration of weights assigned to the parameters based on property type, community preference, or RWA policy. Once weights are configured, the Scoring Module (110) processes tenant behaviour data and calculates parameter-wise scores using scoring algorithms. The Normalization and Aggregation Module (112) then standardizes the parameter scores and combines them using the configured weights to generate a final tenant reliability score.

Following this, the Report Generation Module (114) compiles tenant evaluation reports which include parameter scores, final score, and qualitative feedback. These reports are visually presented to stakeholders through the Presentation Module (116). For collaborative approvals, the Collaborative Decision Interface (118) allows landlords and RWAs to jointly review and authenticate tenant decisions.

Upon approval, the Agreement Automation Module (120) is triggered, generating a tripartite agreement between the landlord, tenant, and RWA. The agreement is digitally signed in sequence, and stored securely. Once fully executed, the Community Access Control Module (122) issues QR-coded, time-bound access credentials to the tenant for secure community entry.

Referring to FIG. 2, the method for scoring tenants begins with the Data Collection step (202), where tenant attributes are retrieved from various sources. The system proceeds to Parameter Identification (204), selecting evaluation parameters such as payment timeliness, damage history, or complaint frequency. These parameters are then subjected to Weight Assignment (206) based on predefined criteria. Additional context-specific feedback from landlords or neighbors is collected in Feedback Collection (208). The core computational process occurs in the Score Calculation step (210), after which the system initiates Tenant Report Generation (212) and finally proceeds to Report Delivery (214), making the evaluations accessible to landlords for action.

FIG. 3A to FIG. 3E illustrate the digital tripartite agreement workflow. In FIG. 3A, upon tenant approval (301), the system triggers agreement generation (302), and sends a secure signing link to the landlord via SMS or messaging applications (304). As shown in FIG. 3B, the landlord reviews the agreement (305), authenticates their identity, and signs digitally (306). The system verifies the signature and marks the agreement as partially signed (306).

In FIG. 3C, the tenant receives the signing link, verifies their identity (308), signs the agreement (307), and submits it to the system. FIG. 3D represents the RWA signature stage, where the link is forwarded, identity is verified (308), the agreement is signed, and the system finalizes it. As shown in FIG. 3E, the completed agreement is stored securely, and the system generates a QR-coded gate pass (313), which is transmitted to the tenant and linked to the community access terminal.

The tenant scoring system (100) is designed as a modular digital framework that enables automated evaluation, verification, agreement execution, and access provisioning for residential tenancy workflows. As illustrated in FIG. 4A, the system begins with the Registration module (410), where landlords and tenants initiate their onboarding by submitting basic details including identity, contact, and property data. This is followed by Profile Creation (412), where the system constructs digital profiles that consolidate uploaded documentation and previous rental history.

Once profiles are created, a Requesting module (414) enables the landlord or RWA to initiate verification checks such as criminal background, credit score, or prior eviction status. The Approving module (416) handles internal approvals from the RWA or landlord to initiate these checks. Subsequently, the Verification module (420) executes the selected verification tasks either internally or by fetching authenticated data from third-party APIs and public databases.

Referring now to FIG. 4B, the system transitions into report preparation and decision flow. Tenant verification results and historical data are fetched from the Database (422). The Analysis module (426) processes this raw data using filtering rules, risk markers, and statistical summarization techniques. These outputs feed into the Scoring module (428) which applies a weighted scoring model to generate a composite tenant reliability score. This score reflects behaviour metrics such as payment discipline, property care, and social conduct. Finally, the Decision module (430) uses these scores to assist landlords and RWAs in accepting or rejecting tenant applications. The decision interface may offer collaborative features such as comment logging, approval stamping, and scoring comparison across candidates.

In FIG. 4C, the system continues into the digital contract and entry phase. Upon tenant approval, an Agreement Form module (432) generates a customizable, legally valid tripartite agreement. This agreement includes predefined clauses and property-specific terms. The Signatures module (434) manages the collection of digital signatures from the tenant, landlord, and RWA. It may incorporate timestamping, identity verification, and digital certificates. Once the document is signed and validated, the Access Enablement module (436) generates a QR-code-based access pass and updates the property’s smart gate or IoT entry system. This enables move-in on the scheduled date with traceable authorization.

Finally, FIG. 4D maps the interaction between key system entities: the Tenant, Landlord, and RWA. These users communicate via a central Server through the user interface. Tenants apply for access and complete agreements, landlords evaluate score reports and initiate verifications, and RWAs participate in decisions and document authorization. The arrows indicate bidirectional data flow and shared control over agreement and access decisions. The system architecture ensures secure, traceable collaboration between all stakeholders in the rental lifecycle.

The present invention finds its application in a wide range of residential and commercial tenancy management scenarios, particularly in gated communities, apartment complexes, co-living spaces, and rental housing societies. It is equally applicable in managed housing platforms, housing rental aggregators, and institutional accommodations such as hostels and PGs where streamlined onboarding, verification, and tenant tracking are essential. The system is adaptable to single-unit landlords as well as large property managers overseeing multiple properties. Further, it serves as an integrated platform for Resident Welfare Associations (RWAs) to enforce community norms through controlled tenant approvals and secure access provisioning. By offering a unified scoring mechanism, it enables micro-level assessments in co-rental models as well as macro-level evaluations for portfolio management across housing blocks.

The invention significantly improves operational efficiency by automating key steps that were previously fragmented and manual. Among the key advantages is the ability to standardize tenant evaluation through a data-driven scoring engine that eliminates subjective biases. The scoring engine integrates structured and unstructured data, assigns configurable weights to behavioral parameters, and generates reliability scores that are statistically normalized for cross-comparison. Landlords are empowered with an objective, real-time measure of tenant suitability, enabling better tenant selection and reduced risk of defaults, conflicts, or property misuse.

Another advantage is the secure and tamper-resistant digital agreement workflow. The sequential digital signing feature eliminates the need for physical document handling while ensuring full traceability and legal enforceability. This is especially advantageous in large housing societies where centralized document control is essential. The blockchain-backed agreement log further enhances trust and immutability in sensitive transactions.

The QR-based access provisioning is yet another advantage that aligns with modern community management standards. By linking agreement execution with gate pass generation, the system ensures that only approved tenants gain physical access to the property. This closes the security loop and prevents unauthorized occupation or movement within the community premises.

The modularity of the system ensures that it can be customized for use in compliance-heavy jurisdictions where mandatory verifications such as police clearance or background checks are required. Similarly, in technology-friendly smart cities, the system can integrate directly with IoT-enabled security infrastructure.

To ensure reliability and conformity with digital contract standards, the system was tested against widely accepted technical and usability metrics. The agreement workflow modules conform to digital signature standards under the Information Technology Act, 2000 (India), and are compatible with Aadhar eSign and other licensed Certifying Authority APIs. The QR-based access credentials were tested using ISO/IEC 18004:2015-compliant scanners and demonstrated 100% read accuracy under standardized lighting and environmental conditions. The backend scoring algorithm was benchmarked using historical tenant datasets and validated through receiver operating characteristic (ROC) analysis, achieving an AUC (Area Under Curve) of 0.91, indicating strong predictive performance for risk classification.

User acceptance testing (UAT) was conducted in partnership with property managers and RWAs over a 3-month pilot involving 50 tenant approvals. The system reduced onboarding time from an average of 7 days to 2.3 days, while maintaining 100% agreement compliance and reducing access errors to zero during the test period. Feedback from stakeholders confirmed ease of use, improved transparency, and high confidence in the tenant selection outcomes.

In summary, the invention offers a comprehensive, standards-compliant, and field-tested solution to tenant screening, onboarding, agreement execution, and access control. It combines the strengths of AI-driven decision support, digital workflow automation, and secure access provisioning into a unified system, making it ideal for widespread adoption in residential tenancy management and beyond.
,CLAIMS:5. CLAIMS
We claim:
1. A tenant scoring system (100) for evaluating the reliability and behaviour of tenants in residential or commercial properties, the system comprising:
a user interface module (102) configured to receive tenant-related inputs and display score outputs to landlords and Resident Welfare Associations (RWAs);
a data collection module (104) configured to aggregate tenant data from multiple structured and unstructured sources including rental history, feedback forms, and regulatory records;
a parameter identification module (106) configured to determine one or more evaluation criteria including timely payments, maintenance compliance, and complaint history;
a weighting module (108) configured to assign predefined weights to each parameter;
a scoring module (110) configured to compute a composite score based on the assigned weights and parameter inputs;
Characterized in that,
the scoring module (110) includes a machine-learning sub-module trained using historical tenant behavioural data, configured to detect anomalies in behaviour patterns and generate predictive risk scores;
the normalization and aggregation module (112) is configured to normalize the computed parameter scores using statistical models such as Z-score or min-max scaling, and to aggregate said normalized scores to compute a final tenant reliability score;
a report generation module (114) is configured to generate encrypted and digitally verifiable tenant score reports in real time, including parameter-wise breakdown, predictive insights, and behaviour risk classification;
the agreement automation module (120) is configured to initiate a tripartite digital agreement workflow between landlord, tenant, and RWA using secure, timestamped signing links and blockchain-based verification;
the community access control module (122) is configured to generate a QR-coded, time-bound digital access pass integrated with an IoT-enabled gate management system, upon successful execution of the digital agreement.

2. The system as claimed in claim 1, wherein the user interface module (102) is implemented as both a web-based dashboard and a mobile application, comprising role-based access control, two-factor authentication, and dynamic visualization of tenant score histories.

3. The system as claimed in claim 1, wherein the data collection module (104) further comprises an API gateway configured to integrate with external platforms including rental agency databases, credit bureaus, and government regulatory systems, ensuring secure and authenticated data exchange.

4. The system as claimed in claim 1, wherein the parameter identification module (106) is dynamically adaptive, allowing landlords and RWAs to select or deselect evaluation parameters from a configurable list based on property-specific or community-specific risk factors.

5. The system as claimed in claim 1, wherein the weighting module (108) includes a rule engine that stores multiple weighting profiles corresponding to property types such as apartment, villa, or co-living spaces, enabling automatic selection of a profile based on input metadata.

6. The system as claimed in claim 1, wherein the scoring module (110) incorporates a machine learning model selected from a group comprising decision tree classifiers, random forest models, or multilayer perceptrons, trained on labeled datasets containing tenant behavior records.

7. The system as claimed in claim 1, wherein the normalization and aggregation module (112) utilizes Z-score standardization for numerical attributes and one-hot encoding for categorical attributes before computing a final composite score.

8. The system as claimed in claim 1, wherein the agreement automation module (120) is further configured to embed blockchain-based transaction hashes within the digitally signed tripartite agreement documents, enabling immutable audit trails and non-repudiable digital evidence.

9. The system as claimed in claim 1, wherein the community access control module (122) is integrated with an MQTT-based communication layer to transmit QR-based access credentials securely to IoT-enabled smart gates, facilitating automated tenant check-in.

10. A computer-implemented method for evaluating and scoring tenants using a tenant scoring system (100) as claimed in claim 1, the method comprising the steps of:
receiving tenant-related data through the user interface module (102);
aggregating structured and unstructured data from multiple sources using the data collection module (104);
identifying one or more tenant evaluation parameters using the parameter identification module (106);
assigning parameter weights using the weighting module (108) based on preconfigured rule sets;
computing parameter-wise scores and generating an overall tenant reliability score using the scoring module (110) in conjunction with an AI-based prediction engine;
normalizing and aggregating the computed scores using the normalization and aggregation module (112);
generating a digitally signed tenant score report using the report generation module (114);
initiating a blockchain-secured digital signing sequence of a tripartite agreement via the agreement automation module (120); and
provisioning access to the property using the community access control module (122), which generates a QR-coded pass delivered to the tenant and validated at IoT-connected entry points.

6. DATE AND SIGNATURE

Dated this 21st day of May 2025
Signature

(Mr. SRINIVAS MADDIPATI)
IN/PA 3124
Patent Agent