We use cookies to provide you with a better browsing experience and to analyze site traffic. By continuing to use our website, you consent to the use of these cookies. Learn more
Our customer is in Electronic Design Automation industry and enables electronic systems and semiconductor companies to create the innovative end products that are transforming the way people live, work and play. Its software, hardware and IP are used by customers to deliver products to market faster. The company helps their customers develop differentiated products—from chips to boards to intelligent systems—in mobile, consumer, cloud, data center, automotive, aerospace, IoT, industrial and other market segments.
The customer’s finance team was looking to streamline their Account Receivables (AR) since they were not efficiently managed, were thus underperforming and directly impacting overall financial performance of the company. The team was looking to address the problem of reducing outstanding receivables through improvements in the collections strategy. Specifically, they wanted to see if Machine Learning could be used to build models for predicting the payment outcomes of newly created invoices, thus enabling customized collection actions tailored for each invoice or customer. Business outcome & success criteria sought was to build models that can predict with high accuracy if an invoice will be paid on time or not and can provide estimates of the magnitude of the delay.
In terms of technology, the customer had a large on-premises SAP landscape and the invoices were stored in SAP ECC system with BW NetWeaver version 7.5. The customer’s IT team who was supporting the finance team in this initiative had been trying to get the invoices out of SAP ECC using Azure Data Factory and thereon transfer them to Azure Synapse for downstream analytics. They were able to extract and transfer the full data load but were not able to transfer the delta loads to update the changes to the full data that was already stored in Azure Synapse. The major challenge faced by the team with ADF in managing the ‘Change Data Capture’ was becoming a showstopper for the whole project.
A3S has a custom built, patent pending automated data migration technology that can ingest data from wide variety of data sources such as SQL, Oracle, SaaS applications like Salesforce, Dynamics 365, AWS S3 and appliances such as Netezza, Teradata etc. and transfer to Azure Synapse. Automated data migration from source system to Azure Synapse has been built with ‘Zero Code 100% Automated’ approach and with just few clicks data transfer is initiated and completed without any manual effort to write code, create & manage pipelines etc. Once the data is in Azure Synapse, A3S provides fully automated analytics as a service that has prebuilt, pretrained machine learning models that can tackle vast number of business scenarios and use cases. Customers just need to provide details of the data to be analyzed and in just few clicks the ML driven insights are available for use.
The customer used the automated data migration to transfer the full load from SAP ECC to Azure Synapse. And subsequently, they scheduled the delta load transfers based on their requirements. The delta load transfer can be triggered manually as well so they have complete flexibility.
Once the full and delta load issue was resolved and all the invoices were available in Azure Synapse, the customer thereon used A3S’ automated data governance functionality to put in place all their organizational data access, management and security policies.
As the final step, the customer used A3S’ fully automated analytics as a service and leveraged pre trained predictive ML models to conduct their AR analysis. They successfully trained and tested multiple variants to create a set of models that they would be using to analyze all their invoices on regular basis to streamline and efficiently manage the account receivables.
Customer was able to achieve this end-to-end scenario from data ingestion to analytics within a week and thereon were able to spend time on tackling the business problem. With this initial experience with A3S, customer realized that Azure platform can be leveraged much more effectively with A3S to solve their business problems and they need not become Azure gurus to get the best that the platform has to offer. It is just the start and there are already many other initiatives being planned by other business teams to use A3S and leverage Azure for all their analytics requirements.