Description:Preamble to the Description
[0001] The following specification describes the invention and the manner in which it is to be performed:
DESCRIPTION OF THE INVENTION
Technical field of the invention
[0002] The present invention relates to a system for multi-dimensional due diligence with risk analysis that assesses an array of risks associated with an individual or a company. More specifically, the invention relates to a due diligence system that incorporates a comprehensive framework for identifying, analysing and monitoring legal, civil, criminal and financial risks through a multi-layered examination of individuals, companies, and their associated networks. The present invention further discloses a method for conducting a multi-dimensional due diligence beyond the individual or the company to evaluate the potential risks related to money laundering, fraud, corruption, and regulatory non-compliance.
Background of the invention
[0003] Due diligence is a comprehensive investigation, verification, and analysis of information that is undertaken especially in the context of businesses and financial transactions to assess different risks and to ensure regulatory compliance. Different organizations such as financial institutions, insurance companies, gaming operators, healthcare providers, and real estate firms must ensure comprehensive compliance with Anti-Money Laundering (AML) and Know Your Customer (KYC) regulations. However, the changing regulations, accompanied by inconsistent KYC processes across the globe in different jurisdictions are creating a significant operational burden on the financial institutions.
[0004] Traditional due diligence practices generally involve manual review of documents, basic identity verification, and background checks that focus primarily on the individual or the company under examination. The current industry standard for completing due diligence processes approximately takes 3-4 days, but leaves a substantial gap in risk assessment as the process fail to identify risk factors that emerge from a broader network of relationships surrounding the primary subject, particularly for the KYC and AML-based risk assessment, which is a deep concern for most of the financial institutions.
[0005] Various patent applications have attempted to address the challenges through different technological solutions that identifies the potential risks associated with the individuals and the companies. For instance, the patent application No. AU2019380450A1, titled “Systems and methods for anti-money laundering analysis” discloses a computer-implemented method that utilizes machine learning technology to detect and investigate potential money laundering activities. The method comprises the steps of obtaining a dataset of multiple accounts with their corresponding variables including financial transactions; analyzing the obtained dataset using a trained algorithm to generate money laundering risk scores for each account holder; and identifying the specific account holders for further investigation based on the risk scores. The invention enables an improved identification of suspicious activities of anti-money laundering (AML) than the traditional methods.
[0006] Patent application No. US20120116954A1, titled “Automated global risk management” discloses a computerized system for analysing and quantifying the risks associated with different financial transactions. The system maintains a comprehensive database that correlates various risk variables such as world events, government advisories, and other information sources with potential risks for financial institutions. The system generates a risk quotient using a weighted algorithm that indicates the level of risk associated with a specific financial transaction or an account. Further, the risk quotient is monitored periodically, throughout a transaction, or on demand. The system helps the financial institutions to manage their risks related to a particular entity or a transaction and creates a log file that helps to reduce the adverse effects connected to the problematic accounts.
[0007] Patent application No. US7805362B1, titled “Methods of and systems for money laundering risk assessment” discloses a method and system for evaluating money-laundering risk associated with an individual. The method comprises the steps of collecting specific data about the individual such as the geographic information, personal information, and product information; determining the risk values for each of the three information categories; applying weighting factors to each of the determined risk values; and, calculating a comprehensive money-laundering risk score by summing the weighted risk values. The method provides an objective framework for financial institutions to assess and quantify potential money laundering risks posed by the individuals.
[0008] Despite these advancements, there remains a need for a more comprehensive due diligence system that provides a multi-dimensional risk assessment framework by considering both direct and indirect associations, as well as legal, civil, criminal, and financial risks, while enabling real-time threat monitoring.
Summary of the invention
[0009] The present invention addresses the limitations of the prior art by disclosing a system for multi-dimensional due diligence with risk analysis that extends beyond an individual or a company by considering the related parties such as the family members and business associates for creating a comprehensive risk profile of the primary subject.
[0010] The multi-dimensional due diligence system comprises an integrated architecture with specialized modules to provide a significantly improved risk assessment than the traditional systems of due diligence. The system comprises an input data module that receives only basic data from a primary subject, such as full name, date of birth, and current address in the case of an individual, or company name, registered address, and Employer Identification Number (EIN) in the case of a corporate entity. The received basic data is transmitted to a data gathering module, that retrieves (gathers) additional subject-specific data such as previous addresses, contact information, identification documents, and known associations for the individuals, and incorporation records, regulatory filings, shareholding patterns, and information about directors and key management personnel for the companies. The data gathering module further gather data related to legal dispute, criminal background, financial crime, sanctions, and Politically Exposed Person (PEP) identification by querying multiple jurisdictional databases and compliance registries on the primary subject. All gathered data is transmitted to a data analysis module where the data are further validated, standardized, and prepared for advanced processing.
[0011] Further, the system comprises a social media analysis module that examines publicly available profiles of the primary subject on different social media platforms such as Facebook, LinkedIn, Twitter, and Instagram wherein potential risk indicators are identified in the social media content, such as incriminating statements or controversial affiliations adhering to data privacy regulations ensuring compliance with the ethical data usage standards.
[0012] Furthermore, the system comprises an association analysis module that maps different networks of relationships such as family members, business partners, and corporate affiliations to enable risk assessment of the associated parties by performing legal dispute check, criminal background verification, financial crime screening, sanctions check and PEP identification on the associations, extending beyond the primary subject.
[0013] Additionally, the system comprises an automated module with news analysis engine that employs web crawling algorithms, Natural Language Processing (NLP), and machine learning models using multiple tools and libraries such as Natural Language Toolkit (NLTK), SpaCy, and TextBlob to continuously scan global news sources, and performs sentiment analysis to classify the news items as negative, positive, or neutral. The automated module further comprises a document parsing engine that uses Portable Document Format (PDF) parsing algorithms through multiple specialized libraries to analyse legal filings, judicial records, and regulatory documents related to the primary subject under consideration.
[0014] Moreover, the system comprises a central data processing and analysis module that integrates and cross-validates data received from different specialized modules, normalizes data and derive meaningful insights. Further a risk scoring and compliance module evaluates the aggregated data received from the central data processing and analysis module and implements a tiered risk classification that categorizes the primary subject as a high risk, medium risk, or a low risk. Further, a report generation module generates a risk scoring report based on the data received from the risk scoring and compliance module.
[0015] In an embodiment, the system operates on a cloud-based infrastructure with a 3-tier architecture comprising a presentation layer, business logic layer, and data layer and supports distinct workflows of due diligence for both the individuals and the companies. The architecture of the system allows an efficient processing and analysis of data that maintains security and scalability.
[0016] The present invention further discloses a method for conducting multi-dimensional due diligence with risk analysis that comprises the steps of collecting, processing, and evaluating data related to the primary subject, either an individual or a company, and their relatives and associates. The method begins with gathering of details of the primary subject and the associated entities, followed by performing criminal and legal record checks, sanctions screening, and political exposure verification. Further, social media analysis is conducted to assess publicly available content for potential risk indicators and the collected data is subjected to cross-referencing to ensure consistency, accuracy, and completeness. Further, risk score of the primary subject is calculated and a comprehensive risk scoring report is generated enabling businesses to make informed decisions about the potential relationships with the primary subject.
Brief description of the drawings
[0017] The foregoing and other features of embodiments will become more apparent from the following detailed description of embodiments when read in conjunction with the accompanying drawings. In the drawings, like reference numerals refer to like elements.
[0018] Figure 1 illustrates a block diagram of a multi-dimensional due diligence system with risk analysis, in accordance with an embodiment of the invention.
[0019] Figure 2 illustrates a flowchart of a method for multi-dimensional due diligence with risk analysis, in accordance with an embodiment of the invention.
[0020] Figure 3 illustrates a flowchart of a method for multi-dimensional due diligence with risk analysis for an individual, in accordance with an embodiment of the invention.
[0021] Figure 4 illustrates a flowchart of a method for multi-dimensional due diligence with risk analysis for a company, in accordance with an embodiment of the invention.
[0022] Figure 5 discloses a block diagram of a cloud server implementing the functionality of the multi-dimensional due diligence system, in accordance with an embodiment of the invention.
Detailed description of the invention
[0023] In order to more clearly and concisely describe and point out the subject matter of the claimed invention, the following definitions are provided for specific terms, which are used in the following written description.
[0024] The term “Polarity score” refers to a numerical score representing the emotional sentiment of a text, ranging from negative to positive, calculated through a computational analysis of linguistic features.
[0025] The term “Primary subject” or the “Subject under consideration” refers to an individual or a company on which the system performs multi-dimensional due diligence along with risk analysis.
[0026] The present invention relates to a system for multi-dimensional due diligence with risk analysis that integrates automated collection and analysis of news and documents, social media monitoring, social network, and risk scoring to provide a comprehensive background checks on individuals and companies for the purpose of regulatory compliance.
[0027] The invention further discloses a method of multi-dimensional due diligence with risk analysis that comprises information gathering, civil, financial and criminal record checks, sanctions screening, political exposure examination, social media analysis, risk score assignment and report generation.
[0028] Figure 1 illustrates a block diagram of a multi-dimensional due diligence system with risk analysis, in accordance with an embodiment of the invention. The system (100) comprises an input data module (101) that receives basic identifying data from a primary subject comprising full name, date of birth, and current address in the case of an individual, or a company name, registered address, and Employer Identification Number (EIN) in the case of a corporate entity.
[0029] The received data is transmitted to a data gathering module (102), that retrieves additional subject-specific data such as previous addresses, contact information comprising phone numbers and email ids, identification documents, and known associations for the individuals. For companies, the data gathering module (102) gathers details such as incorporation records, regulatory filings, shareholding patterns, and information about the directors and key management personnel. The data gathering module (102) further gather data related to legal dispute, criminal background, financial crime, sanctions, and Politically Exposed Person (PEP) identification by querying multiple jurisdictional databases and compliance registries on the primary subject. All gathered data is transmitted to a data analysis module (103) where the data are further validated, standardized, and prepared for advanced processing.
[0030] Further, the system (100) comprises a social media analysis module (104) configured to examine and evaluate publicly available social media profiles and activities of the primary subject. The social media analysis module (104) accesses and analyses data from various social media platforms, such as Facebook, LinkedIn, Twitter, and Instagram, while adhering to applicable data privacy regulations. The social media analysis module (104) identifies potential risk indicators in social media content, including but not limited to incriminating statements, controversial affiliations, or behavioural patterns inconsistent with the disclosed information of the primary subject.
[0031] In one embodiment, the social media analysis module (104) performs limited automated checks on the publicly available profiles, wherein the reviews requiring contextual interpretation of posts or sentiments are conducted manually. In another embodiment, the social media analysis module (104) employs artificial intelligence (AI)-based sentiment analysis and machine learning models to perform large-scale evaluation of social media data, enabling automated detection of red flags, sentiment classification, and behaviour profiling, while ensuring compliance with regulatory and privacy standards. In yet another embodiment, the social media analysis module (104) operates in a hybrid mode, wherein the outputs of automated analysis are further verified through manual review. The findings generated by the social media analysis module (104) are transmitted to the central data processing and analysis module (107) for subsequent integration and evaluation.
[0032] Further, the system (100) comprises an association analysis module (105) that finds a network of relationships such as family members, business partners, corporate affiliations, and other relevant connections that impacts the risk assessment of the primary subject. The association analysis module (105) gather data related to legal dispute, criminal background, financial crime, sanctions, and Politically Exposed Person (PEP) on the associates of the primary subject. The gathered data is further validated, standardized, and transmitted to the central data processing and analysis module (107) for further processing.
[0033] In one embodiment, the association analysis module (105) operates in a semi-automated manner, wherein certain aspects of relationship mapping between the primary subject and their associates or relatives are performed through automated tools, while verification and link analysis are manually conducted. In another embodiment, the association analysis module (105) utilizes graph-based databases and relationship inference models to automate the detection of associations and the identification of potential risk flags. The findings generated by the association analysis module (105) are provided to the central data processing and analysis module (107) for comprehensive integration with other data sources.
[0034] Further, the system (100) comprises an automated module (106) for performing automated data extraction and analysis from different unstructured sources. The automated module (106) comprises a news analysis engine (106a) that implements web crawling algorithms to continuously scan global news sources, blogs, and media outlets to identify emerging risks associated with the individuals or the companies. In one embodiment, the news analysis engine (106a) employs Natural Language Processing (NLP) algorithms and machine learning models assisted by multiple tools and libraries such as Natural Language Toolkit (NLTK), SpaCy, and TextBlob to perform sentiment analysis, and classifying extracted news items as negative, positive, or neutral based on the calculated polarity scores. The automated module (106) further comprises a document parsing engine (106b) to parse and analyse structured and unstructured documents such as legal filings, judicial records, and regulatory documents related to the primary subject. The document parsing engine (106b) utilizes Refined Named Entity Recognition (Refined NER) that brings in an extra ability to search and map structured and unstructured documents with aspects such as laundering, fraud, fines, and crime. In one embodiment, the document parsing engine (106b) utilizes custom Portable Document Format (PDF) parsing algorithms implemented through different libraries such as pdf_miner and Python-docx to extract vital segments from the legal documents that traditionally requires a manual review.
[0035] The central data processing and analysis module (107) integrates the data received from the automated module (106), social media analysis module (104) and the association analysis module (105), normalizes the received data, and applies analytical algorithms to derive meaningful insights within the received data.
[0036] In one embodiment, the central data processing and analysis module (107) is responsible for collecting, processing, and enriching data from multiple sources, wherein various data formatting and validation steps are performed through automated routines while maintaining manual oversight to ensure accuracy and compliance with applicable regulations. In another embodiment, the central data processing and analysis module (107) employs advanced data pipelines and intelligent Extract-Transform-Load (ETL) processes, thereby enabling high-throughput automated integration and reducing manual intervention.
[0037] Additionally, the system (100) comprises a risk scoring and compliance module (108) that evaluates aggregated data received from the central data processing and analysis module (107), against the specific risk parameters and generates standardized risk assessments.
[0038] The risk scoring and compliance module (108) applies customizable risk scoring methodologies based on multiple weighted factors such as criminal history, legal proceedings, sanctions status, and political exposure, and implements a tiered risk classification system that categorizes the primary subject as high risk (red), medium risk (amber), or low risk (green) based on comprehensive evaluation criteria. In one embodiment, the evaluation of these weighted factors is performed through predefined rule sets and manual judgment to assign the risk classification. In another embodiment, the risk scoring and compliance module (108) implements adaptive scoring algorithms that autonomously learn from historical data patterns and feedback, thereby enabling automated and consistent risk evaluation with minimal manual intervention. Furthermore, the risk scoring and compliance module (108) allows customization of the risk presentation formats.
[0039] Furthermore, the system (100) comprises a report generation module (109) configured to present analysis results in the form of structured and compliant documentation. The report generation module (109) organizes comprehensive findings into a standardized report that adheres to applicable regulatory requirements. In one embodiment, the report generation module (109) utilizes templating engines to populate pre-defined report formats with relevant analytical outputs, supporting evidence, calculated risk scores, and recommendation summaries. In another embodiment, the report generation module (109) employs automated summarization tools and intelligent content generation techniques to construct complete due diligence reports with minimal manual intervention. This configuration facilitates scalable and consistent report delivery while maintaining accuracy and compliance standards.
[0040] In an embodiment for analysing the individual due diligence, the system (100) receives basic information of the subject such as name, address and date of birth through the input module (101). The system (100) gathers and analyse further personal identifiers through the data gathering module (102) that retrieves and analyzes additional subject-specific data such as previous addresses, contact information such as phone numbers and email ids, identification documents, and known associations of the individual. Additionally, the data gathering module (102) gathers data related to legal dispute, criminal background, financial crime, sanctions, and Politically Exposed Person (PEP) identification and the gathered data is validated, standardized for further processing. The system (100) initiates parallel analysis of data through the automated engine (106) that extracts news and relevant legal documents on the primary subject; the social media analysis module (104) that evaluates online presence; and the association analysis module (105) that identifies and analyses family members and business associates for their criminal record checks, sanctions screening, and Politically Exposed Person (PEP) status verification. The central data processing and analysis module (107) integrates these findings and the risk scoring and compliance module (108) evaluates and assigns risk scores to the individual. Finally, the report generation module (109) generates a comprehensive individual profile comprising identity verification, criminal and legal history, social media findings, PEP status and network analysis with the risk classifications.
[0041] Figure 2 illustrates a flowchart of a method for multi-dimensional due diligence with risk analysis, in accordance with an embodiment of the invention. The method (200) for multi-dimensional due diligence with risk analysis comprises the steps of receiving basic identifying data of a primary subject, wherein the primary subject is an individual or a company in step (201). In step (202), additional information related to the primary subject, comprising historical addresses, contact numbers, email addresses, identification details, legal disputes, criminal records, sanctions status, and politically exposed person (PEP) information are gathered and analysed. Further the gathered and analysed data are validated and standardized the into a uniform format in step (203). In step (204), news analysis is performed by scanning global news sources in real time, processing news content using natural language processing techniques, conducting sentiment analysis, and classifying news articles based on polarity scores. Further in step (205) structured and unstructured legal documents related to the primary subject are parsed, and relevant information is extracted using custom parsing techniques. In step (206), social media profiles of the primary subject are analysed to identify potential risk indicators through the recognition of behavioural patterns and publicly observable activity. In step (207), a network of relationships of the primary subject is identified, comprising family members, business partners, and corporate affiliations. Data related to these associated entities, including legal disputes, criminal background, sanctions, and PEP information is retrieved and analysed by querying multiple jurisdictional and compliance databases. In step (208), the data collected from the various modules and sources is integrated and normalized by identifying common fields, resolving conflicts, and standardizing formats. Finally, in step (209), a comprehensive risk assessment report is generated, comprising a standardized risk score along with analytical findings for informed decision-making and compliance documentation.
[0042] Figure 3 illustrates a flowchart of a method for multi-dimensional due diligence with risk analysis for an individual, in accordance with an embodiment of the invention. The method (300) for multi-dimensional due diligence with risk analysis for an individual, comprises the steps of receiving and gathering basic as well as extensive information of the individual in step (301). The basic information comprises name, address and date of birth of the primary subject or the individual. The extensive information includes but not limited to age, previous addresses, contact number, email addresses, relatives and associates, and businesses (if any) of the individual. In step (302), jurisdiction-specific criminal, and legal record checks are conducted on the individual by accessing multiple databases across various legal jurisdictions to retrieve records of historical legal proceedings associated with both the current and the past residential addresses of the individual. In step (303), sanctions screening is conducted to detect any financial crimes and to ensure compliance with the Anti-Money Laundering / Know Your Customer (AML/KYC) regulations, wherein the individual's identifiers are compared against global sanctions databases and the watchlists. In step (304), political exposure examination of the individual is performed to identify the Politically Exposed Persons (PEP) who presents elevated corruption risks. In step (305), social media profile of the individual is analysed for the incriminating posts through the examination of publicly accessible digital footprints and online behaviour patterns. In step (306), associated parties and relatives are investigated for multi-dimensional risk assessment, extending the analytical scope of the method beyond the primary subject to map the additional risk factors. In step (307), the risk scores are assigned and displayed using flag colours, ratings, or grades based on the analytical findings, facilitating a standardized risk representation for informed decision-making by the businesses and compliance documentation.
[0043] Figure 4 illustrates a flowchart of a method for multi-dimensional due diligence with risk analysis for a company, in accordance with an embodiment of the invention. The method (400) for multi-dimensional due diligence with risk analysis for a company comprises the steps of receiving and gathering basic information of the company comprising the company name, EIN number, and current address; and extensive information comprising contact number, email addresses, alias names, year of establishment and incorporation, and a brief description of the company in step (401). In step (402), legal proceedings and regulatory filings are examined across relevant jurisdictions, wherein the historical court cases, regulatory actions, and compliance records are analysed to identify the legal risks of the company. In step (403), bankruptcy filings records are scrutinized to assess the financial stability and to determine if the company has previously declared bankruptcy and subsequently reestablished its operations. In step (404), the money laundering activities and financial crime indicators are investigated through the analysis of transaction patterns, financial relationships, and involvement in the high-risk business sectors. The indicators comprises various types of fraud such as cheque, credit card, mortgage, medical, corporate, securities, bank, insurance, payment, and healthcare, market manipulation, scams, bribery, embezzlement, forgery, and counterfeiting. In step (405), tax evasions and dishonest tax reporting patterns checks are performed to identify if the company has had issues with the tax authorities regarding tax liability reduction or fraudulent reporting. In step (406) the corporate digital footprint is evaluated through social media analysis and online presence assessment to identify reputational risks and public perception factors. In step (407), associated companies such as parent entities, and subsidiaries are investigated for comprehensive risk assessment. In step (408), background screening is performed on the founders, board of directors and key executives, wherein history of each individual, their affiliations, and risk factors are examined using the method for individual due diligence. Finally, in step (409), a risk scores is generated using color-coded indicators, numerical ratings, or alphabetical grades based on the comprehensive analysis, thereby providing a standardized risk representation to facilitate strategic decision-making and regulatory compliance.
[0044] Figure 5 discloses a block diagram of a cloud server implementing the functionality of the multi-dimensional due diligence system, in accordance with an embodiment of the invention. The cloud server (500) comprises multiple primary functional components such as a processor (501), a storage device (502), a main memory (503), and a communication interface (504) to implement a 3-tier architecture of the system (100) comprising a presentation layer (front-end), a business logic layer (back-end), and a data layer (database).
[0045] In an embodiment, the processor (501) comprises a multi-core Central Processing Unit (CPU) (501a) and compute engine (501b) to execute the processing operations supported by the backend functionality of Node.js. The processor (501) performs the computational tasks such as data normalization, cross-referencing of information across multiple sources, and implementation of risk assessment algorithms. The processor (501) facilitates real-time data processing for both the individual and the company due diligence operations and handle requests from the frontend through the REST API gateway.
[0046] Further, the storage device (502) incorporates Solid-State Drive / Hard Disk Drive (SSD/HDD) technologies enabling data storage capabilities. In an embodiment, the storage device (502) interfaces with Mongo Database (MongoDB) Atlas, a cloud-based NoSQL database solution. The storage device (502) maintains textual data in the MongoDB collections and stores larger files such as legal documents and reports in the Amazon S3 storage with their corresponding reference paths saved in the database. The storage device (502) supports the data persistence layer for all structured and unstructured data processed during different operations for performing the due diligence.
[0047] Further, the main memory (503) comprises Random Access Memory (RAM) storage and data caching functionality for temporary data storage to facilitate the data processing. The main memory (503) stores active user sessions, cached query results, and intermediate data structures required during multi-dimensional risk assessments. The main memory (503) further maintains temporary copies of frequently accessed data to reduce latency and enhance system performance during the intensive operations such as social media analysis and document parsing.
[0048] Moreover, the communication interface (504) comprises at least a network card (504a) and a REST API (504b) gateway to facilitate external communications between the frontend and the backend. The communication interface (504) manages all the incoming and the outgoing network traffic, processes API requests from the frontend application, validates authentication tokens, and routes data to backend services such as to the news analysis engine (105a) and the document parsing engine (105b). The communication interface (504) establishes secure connections for accessing external data sources such as public records, government databases, and social media platforms.
[0049] In an embodiment, the cloud server is deployed on a cloud object storage service, ensuring high availability, security, and scalability. The system (100) utilizes the cloud object storage service for the file storage, wherein the file paths are stored in the MongoDB, and communication between the frontend and backend components is facilitated by the REST APIs. The entire processing occurs within the cloud environment, allowing for seamless integration between the presentation layer, business logic layer, and the data layers of the system (100).
[0050] The present invention offers significant advantages in the field of regulatory compliance and risk management by providing a multi-dimensional approach to due diligence addressing the complexity of global regulatory requirements. The system (100) integrates the news analysis engine (106a) and document parsing engine (106b) that significantly reduces the time for regulatory compliance check by automating the data collection and validation. The news analysis engine (106a) scans global news sources for emerging risks, and the document parsing engine (106b) automatically cross-references unstructured data from multiple sources, accelerating the method of due diligence. The news analysis engine (106a) further updates the users in real time, with the latest news and events that could impact their risk profiles. This proactive approach to risk detection is valuable in fast-moving industries where risks emerges suddenly. Further, the document parsing engine (106b) automates the data validation and cross-referencing from multiple sources such as public records, government databases, social media, reducing human error and ensuring more accurate and comprehensive due diligence results. The system (100) is customizable for various industries such as gaming, banking, insurance, healthcare, and more.
[0051] Moreover, the incorporation of social media analysis module (104) and association analysis module (105) provides a significant advancement over the conventional methodologies of due diligence check that rely primarily on official records. The association analysis module (105) identifies indirect risk factors by extending the due diligence to examine connections with relatives, business partners, and associated entities, thereby enabling the individual and companies to identify potential risk transfer vectors leading to heightened regulatory scrutiny, reputational damage, or financial liabilities.
[0052] The system (100) further comprises the risk scoring and compliance module (108) and the report generation module (109) allowing the individual and companies to customize their specific regulatory and risk management needs. Users can choose from flag colours, numerical ratings, or letter grades to represent risk profiles in a way that best suits them.
[0053] Furthermore, the system (100) adheres to applicable data privacy regulations by implementing secure data handling practices, including encryption, controlled access, and secure transmission protocols. By ensuring that personal and corporate data is well protected throughout the due diligence process, the system (100) upholds user trust and supports legal compliance.
[0054] Finally, the system (100) meets the global regulatory standards, ensuring the companies remain compliant with the local and the international laws.
[0055] Having generally described this invention, a further understanding can be obtained by reference to a specific example, which is provided herein for the purpose of illustration only and is not intended to be limiting unless otherwise specified.
Example 1: Multi-dimensional due diligence system for a high-risk financial industry user
[0056] As an illustrative example, consider a scenario where a financial institution implements the multi-dimensional due diligence system (100) to evaluate a potential individual. The system (100) first gathers basic data of the individual such as full legal name, date of birth, and current address of the individual using the input data module (101). The system (100) subsequently retrieves and gathers additional subject-specific data including but not limited to contact numbers, email addresses, and historical residential addresses of the individual as well as known relatives and associates through the data gathering module (102).
[0057] The data gathering module (102) further gather data related to legal dispute, criminal background, financial crime, sanctions, and Politically Exposed Person (PEP) identification by querying multiple jurisdictional databases and compliance registries on the potential individual. In this case, the analysis reveals that the individual previously served as a regional economic advisor to a government ministry, thereby qualifying as a Politically Exposed Person (PEP) of medium risk.
[0058] Further, the automated module (106) comprising the news analysis engine (106a) scans global news sources in real-time using natural language processing techniques and identifies several news items mentioning the individual in connection with different business ventures but does not find any negative sentiment indicators. In parallel, the document parsing engine (106b) parses legal filings and regulatory documents, extracting vital segments that reveal two historical civil litigation cases against the individual involving disputed business transactions.
[0059] Further, the social media analysis module (104) examines the publicly accessible profiles of the individual across various platforms, applying pattern recognition techniques and identifies potentially concerning connections with two individuals who were previously investigated for financial litigations. The social media analysis module (104) flags these connections as risk indicators and transmit the data to the central data processing and analysis module (107) requiring further scrutiny.
[0060] Further, the association analysis module (105) finds the relatives and associates of the individual wherein the analysis reveals that the individual's brother-in-law currently holds a position within the country's tax authority, elevating the composite political exposure risk. Further analysis uncovers an indirect business connection to a corporate entity under regulatory investigation in a neighbouring jurisdiction. The association analysis module (105) transmit the collected data to the central data processing and analysis module (107) for further analysis.
[0061] The central data processing and analysis module (107) consolidates and normalizes the data received from the various modules, resolves data inconsistencies, and passes the refined data to the risk scoring and compliance module (108).
[0062] The risk scoring and compliance module (108) evaluates the aggregated information against predefined risk parameters and applies a customizable scoring methodology based on weighted factors, including litigation history, political exposure, and risks arising from associated entities. Based on the analysis, the system (100) assigns a risk score of 68/100 (medium-high risk) with an amber flag.
[0063] Finally, the report generation module (109) organizes the comprehensive findings into a standardized report, accompanied by specific compliance recommendations including enhanced transaction monitoring, source of funds verification, and quarterly relationship reviews. This comprehensive risk profile enables the financial institution to make an informed onboarding decision and implement appropriate risk-based controls, customized to the identified risk vectors.
[0064] The above example demonstrates the multi-dimensional approach of the system (100) that identifies risk factors through a social network analysis and political exposure examination which would remain undetected using conventional due diligence checks.

Reference numbers:
Components Reference Numbers
System 100
Input Data Module 101
Data Gathering Module 102
Data Analysis Module 103
Social Media Analysis Module 104
Association Analysis Module 105
Automated Module 106
News Analysis Engine 106a
Document Parsing Engine 106b
Central Data Processing and Analysis Module 107
Risk Scoring and Compliance Module 108
Report Generation Module 109
Cloud Server 500
Processor 501
Multi-core CPU 501a
Compute Engines 501b
Storage Device 502
Main Memory 503
Communication Interface 504
Network Card 504a
REST API Gateway 504b
, Claims:We claim:
1. A system for multi-dimensional due diligence with risk analysis, the system (100) comprising:
a. an input data module (101) configured to receive and transmit basic identifying information of a primary subject wherein the primary subject is an individual or a company;
b. a data gathering module (102) configured to retrieve multiple additional data related to the primary subject such as one or more previous addresses, contact numbers, email addresses, identification documents, legal disputes, criminal background, sanctions, and politically exposed person (PEP) information by querying multiple databases of jurisdictional and compliance registries;
c. a data analysis module (103) configured to validate, standardize, and prepare the gathered data for further processing;
d. a social media analysis module (104) configured to access one or more publicly available social media profiles of the primary subject, and apply pattern recognition techniques to identify potential risk indicators comprising incriminating statements, controversial affiliations, and behaviour patterns inconsistent with the disclosed information of the primary subject;

e. an association analysis module (105) configured to:
i. find a network of relationships of the primary subject comprising one or more family members, business partners, and corporate affiliations; and
ii. retrieve and analyse multiple data related to the network of relationships of the primary subject such as legal disputes, criminal background, sanctions, and politically exposed person (PEP) information by querying multiple databases of jurisdictional and compliance registries;

f. an automated module (106) to receive and process the data from the data analysis module (103) wherein the automated module (106) further comprises:
i. a news analysis engine (106a) configured to:
scan and extract one or more news items in a real time from multiple global news sources, blogs, and media outlets through an implementation of natural language processing; and
perform sentiment analysis of the extracted news items by calculating a polarity score, and classifying the extracted news items as negative, positive, or neutral;
ii. a document parsing engine (106b) configured to:
parse multiple structured and unstructured documents comprising one or more legal filings, judicial records, and regulatory documents;
utilize a custom Portable Document Format (PDF) parsing technique, implemented through multiple libraries such as pdf_miner and Python-docx; and
extract one or more segments from the structured and unstructured documents for manual review;

g. a central data processing and analysis module (107) configured to:
i. receive, integrate and normalize multiple data received from the social media analysis module (104), association analysis module (105), and the automated module (106);
ii. resolve one or more conflicting information related to the primary subject and the network of relationships through comparison and cross-referencing of multiple source entries; detect and flag data inconsistencies; and generate and transmit a consolidated dataset to a risk scoring and compliance module (108);

h. the risk scoring and compliance module (108) configured to:
i. evaluate the consolidated dataset against a set of risk parameters;
ii. apply customizable risk scoring methodologies based on one or more weighted factors comprising criminal history, legal proceedings, sanctions status, and political exposure; and
iii. implement a tiered risk classification categorizing the primary subject as a high risk (red), medium risk (amber), or low risk (green); and
i. a report generation module (109) to receive data from the risk scoring and compliance module (108), and generating a standardized report adhering to one or more regulatory requirements;
wherein the system (100) extends the risk assessment to the associated parties, mapping relationships with the primary subject for multiple degrees of connections.

2. The system (100) as claimed in claim 1, wherein the basic identifying information of the primary subject comprises a name, date of birth, and address for an individual; and a company name, address, and Employer Identification Number (EIN) for a company.

3. The system (100) as claimed in claim 1, wherein the natural language processing technique utilized by the news analysis engine (106a) comprises the inclusion of contextual text analysis and language pattern recognition.

4. The system (100) as claimed in claim 1, wherein the document parsing engine (106b) is configured to apply one or more advanced text entity recognition techniques to map people and organizations, and to track multiple risk-related aspects such as laundering, fraud, financial penalties, and criminal activities within the analysed documents.

5. A method for multi-dimensional due diligence with risk analysis, the method (200) comprises the steps of:
a. receiving basic identifying data of a primary subject, wherein the primary subject is an individual or a company (201);
b. gathering and analysing additional information related to the primary subject, comprising historical addresses, contact numbers, email addresses, identification details, legal disputes, criminal records, sanctions status, and politically exposed person (PEP) information (202);
c. validating and standardizing the gathered and analysed data into a uniform format (203) ;
d. performing news analysis by scanning global news sources in real time, processing news content using natural language processing techniques, conducting sentiment analysis, and classifying news articles based on polarity scores (204);
e. parsing structured and unstructured legal documents of the primary subject, and extracting vital segments using custom parsing techniques (205);
f. analysing social media profiles of the primary subject to identify potential risk indicators, recognizing patterns of behaviour (206);
g. finding a network of relationships of the primary subject comprising one or more family members, business partners, and corporate affiliations; and retrieve and analyse multiple data related to the network of relationships of the primary subject such as legal disputes, criminal background, sanctions, and politically exposed person (PEP) information by querying multiple databases of jurisdictional and compliance registries (207);
h. integrating and normalizing data from multiple sources by identifying common data fields, standardizing data formats, and comparing and verifying data entries (208); and
i. generating a comprehensive risk assessment report with a standardized risk score (209).
6. The method (200) as claimed in claim 5, wherein the method (200) further comprises the step of applying one or more jurisdiction-specific search parameters for performing plurality of criminal and legal record checks of the primary subject to ensure compliance with the local regulations.

7. The method (200) as claimed in claim 5, wherein the standardized risk score calculation comprises assigning and computing weighted values to multiple risk factors including criminal history, legal proceedings, sanctions status, political exposure, and risks associated with connected parties of the primary subject to generate a comprehensive risk assessment value.