The analysis is on an App based product which is a personal line of credit domain. The data consists of customer demographics, transactions, number of download, install, registrations, etc. The data is retrieved from the DB which consists of the customer details from the registration to the approval. The environment used for the analysis of the data is R an Python. As the data is raw and unsupervised, different clustering algorithms like A-priori Algorithm, Hierarchical clustering and K-means are implemented to clean and find some reliable patterns, so that it can be used further. Machine learning algorithms like Random Forests, SVM, and logistic regression are used for the prediction of the default customers on the transaction data. The further analysis is an ongoing process and accordingly analysis is done.

The credit card fraud detection features uses user behavior and location scanning to check for unusual patterns. These patterns include user characteristics such as user spending patterns as well as usual user geographic locations to verify his identity. If any unusual pattern is detected, the system requires revivification. The system analyses user credit card data for various characteristics. These characteristics include user country, usual spending procedures. Based upon previous data of that user the system recognizes unusual patterns in the payment procedure. So now the system may require the user to login again or even block the user for more than 3 invalid attempts. Build a classification model (using techniques like Logistic Regression, Decision Tree, Random Forest, Boosting, Bagging) to classify good and bad customers. Core Features: The system stores previous transaction patterns for each user. Based upon the user spending ability and even country, it calculates users characteristics. More than 20 -30 %deviation of users transaction(spending history and operating country) is considered as an invalid attempt and system takes action.

We had developed workflow for ABSA Bank collaboration with Barclays in South Africa. Home Loan Customer Fulfilment Payments (HLCF-Payments) business process using Blueprism processes, components, business objects, environment variables , work queues and credentials. 1- Prepayment models - Prepayment is a problem in loan contracts for banks. Use loan data to predict customers could potentially prepay. We build another model in parallel to this to know if a customer prepays, when is he likely to prepay in the life time of the loan (time to prepay). we also build a model to know how much loss the company would incur if a section of the portfolio of customer prepay in future. 2 - Fraud Model - These models are being used to know if a particular transaction is a fraudulent transaction. Historical data having details of fraud and non-fraud transactions can be used to build a classification model that would predict chances of fraud happening in a transaction. Since we normally have high volume of data, one can try not just relatively simpler models like Logistic Regression or Decision trees but also should try more sophisticated ensemble models.

Inquiry is a User Interface Frqmework, used for generating a CITI Reports. It Act as central point to generate the report and it take data source from many databases like mysal,sysbase, oracal etc. Inquiry Framework has many applications in it.Each application has certain set of domains to be executed on. These Domains are based on database where the application hits.

Campusnext is a web based application.This project is used to maintain the Employee Management, Student Lifecycle Management, Examination Management, University Management, Faculty Lifecycle Management and Dues and Payment Management. Implemented our Campus Next Solution to Perform Student Administration activity from applicant to alumni which will coordinate with HRMS & finance modules. Implemented a campus administration system for their hostels, gymkhana, and security purposes.

The analysis is on an App based product which is a personal line of credit domain. The data consists of customer demographics, transactions, number of download, install, registrations, etc.

The data is retrieved from the DB which consists of the customer details from the registration to the approval.

The environment used for the analysis of the data is R an Python.

As the data is raw and unsupervised, different clustering algorithms like A-priori Algorithm, Hierarchical clustering and K-means are implemented to clean and find some reliable patterns, so that it can be used further.

Machine learning algorithms like Random Forests, SVM, and logistic regression are used for the prediction of the default customers on the transaction data.

The further analysis is an ongoing process and accordingly analysis is done.

Algorithm uses a combination of techniques in two topics; face detection and recognition. The face detection is performed on live acquired employee images. Processes utilized in the system are facial feature extraction and face image extraction on a face candidate. Then face classification methods like deep learning libraries (dlib and face recognition), KNN algorithm and CNN are implemented on the live capture data.

The system is tested with a database generated in the laboratory. The tested system has acceptable performance to recognize faces within intended limits. System is also capable of detecting and recognizing multiple faces in live acquired images

The credit card fraud detection features uses user behavior and location scanning to check for unusual patterns. These patterns include user characteristics such as user spending patterns as well as usual user geographic locations to verify his identity. If any unusual pattern is detected, the system requires revivification.

The system analyses user credit card data for various characteristics. These characteristics include user country, usual spending procedures. Based upon previous data of that user the system recognizes unusual patterns in the payment procedure. So now the system may require the user to login again or even block the user for more than 3 invalid attempts.

Build a classification model (using techniques like Logistic Regression, Decision Tree, Random Forest, Boosting, Bagging) to classify good and bad customers.

Hulft is a web based application. This application is used to install the software at remote systems and local systems.

Transfer:

Transfer feature in bigly is internally called by HULFT.command_list describes atomic functionalities inside engine, through which a bond agent operates file transfer related operations.

Integration:

Integration in bigly is internally called as DataSpider Servista (DSS).
Here are its corresponding list of command_dss, by which bond operates integration nodes remotely.