Name: Automate Intercompany Reconciliation in Two-Tier ERP with Machine Learning - SAP S/4HANA Technology Topics
Uploaded: 2021-8-4
Duration: 399 s
Description: Learn how to automate intercompany reconciliation in two-tier ERP with machine learning using SAP S/4HANA.

Share feedback

<p><u><strong>Planned maintenance of Practice Systems</strong></u></p>

Planned maintenance of Practice Systems

Why create an SAP account?

Enhance your learning experience

SAP Learning

Choose your subscription

Manage your subscription

Live Sessions

Hands-on Practice

Certification

My Learning

Ready to start learning?

<div><div>Learn how to automate intercompany reconciliation in two-tier ERP with machine learning using SAP S/4HANA. </div></div>

Automate Intercompany Reconciliation in Two-Tier ERP with Machine Learning - SAP S/4HANA Technology Topics

Hello and warm welcome to this micro learning session. We will see how to automate the intercompany reconciliation in 2T ERP with machine learning technology. My name is Swati Balani and I am the SAP S4 HANA product manager at PCC SAP Labs India. This is the agenda for the session. We will first see the traditional approach with the drawbacks for the intercompany reconciliation And then we'll see how the SAP S4 HANA Cloud offers the benefits and how the machine learning offers the benefits in automating the inter-company reconciliation process. Next, we will see a business use case and a demo in the system to see how the automation works. So traditional inter-company reconciliation is seen as time consuming and labor intensive work. From subsidiaries point of view, there are a lot of discrepancies which needs offline communication to find the root cause and resolve them. And from headquarter point of view, the group accountant finds it difficult to explain the differences and the inconsistencies due to large volume of data and takes much longer time for inter-company elimination, consolidation, and corporate closing. So with SAP S&P HANA Cloud, we get the following benefits. We get predefined rules for auto match. We get flexible upload of subsidiary companies financial data through file upload or APIs or central finance solution. We can standardize the end-to-end business processes across multiple systems. We get pre-delivered best practices content, agility with faster upgrades, with faster innovations, with intelligent technologies like machine learning. We get out-of-the-box integration capabilities and lower TCO with software as a service model. So what are the machine learning benefits? We can automate the labor-intensive work. We can save time, save human efforts, save operation cost. We can increase the matching accuracy, speed up the month-end closing, consolidation, and group reporting. You can increase the transparency and streamline the local closing to corporate closing process. This is a business use case using intelligent machine learning scenario for inter-company reconciliation. Here, tier two is any substrate company on any SAP or non-SAP external system. And tier one is a headquarter running on SAP S4 HANA Cloud or on-premise. Tier two can send the inter-company accounting documents to tier one with APIs, flat files, or center finance solution. Within tier one, the inter-company accounting documents first get matched with the predefined rules set up in the system. And the remaining unmatched documents are sent to SAP BTP, Intelligent Inter-Company Reconciliation Service, for further matching. This intelligent machine learning solution does the line item matching and the matching reason code assignment. And the match documents proposal is then sent back to the headquarter running on SAP S4HANA Cloud or on-premise. The headquarter can further do the inter-company elimination and consolidation and group reporting. So let's look at a system demo for the inter-company reconciliation automation process. So here, the headquarter group accountant logs into the SAP S4HANA Cloud system and opens the Reconciliation Balances Fiori app. Here, C3000 is a substrate company running on any external system, and C1000 is the company running on SAP S4HANA Cloud. Now, since C1000 is within the SAP S4HANA Cloud system, We see the amount getting updated in real time in the Reconciliation Balances Fiori app. Since C3000 is not in SAP S4 HANA Cloud yet, the amount is zero. Next, the group accountant can upload the inter-company accounting financial documents in the SAP S4 HANA Cloud system using the flexible upload of reported financial data Fiori app. So with this app, the file upload for the inter-company accounting documents for subsidiary companies can be done. So after the upload is complete, we see the balance appearing for the subsidy company and the difference amount reducing to 2000 euros which is within the tolerance limit. So next the Group Accountant can go and see these inter-company accounting documents for both leading unit and partner unit and can review the inter-company accounting documents. So here you find a small button which says Auto Match with just one click on this Auto Match button the inter-company accounting documents for the leading unit and the partner units would get matched automatically. So here we see how the matching has happened. In the first case, the matching got picked up with matching type which is exact match and we see the matching rules defined here to pick from these GL accounts for the group currency amount within the tolerance limit of 10,000. This was about the auto match with the SAP S4 HANA cloud predefined rules. Next we see the machine learning capabilities and we see here there are three new tiles and some predefined jobs available for the machine learning. The first one is the schedule training job. This would train the machine for doing the auto match. Next we see the schedule inference job. This would send the inter-company accounting documents to the machine for auto match and we also get a machine learning monitor which would show us the status of the inter-company accounting document matching and reconciliation with the machine learning. So once the documents are sent back by the machine learning application, the status can be seen in the monitor. So now the group accountant would go to the the manage assignments theory app and would select the matching method for machine learning. So here you see the inter-company accounting documents for both leading unit and partner unit. And there's a button which says auto match with machine learning. With just one click to this button, these documents are sent to the machine learning application on SAP BTP for further matching. And this is the monitor that we see here. This monitor collects the data and gives the status once the results are received. We can also see the log for the results. Then the group accountant can check the results on the manage assignments app, and can see the auto-matched documents and assignments in the screen below. So as you see here, 5,000 assignments got matched. Next, the group accountant can see the details of these auto-matched assignments. And here, as we see in this case, the inter-company accounting documents got matched with confidence level of 87.9%. So this was all about the machine learning capability with manage assignments theory app. And next, we see the schedule inference job. Now here, we see that we have a ready-made job template available, which is the machine learning inference for inter-company matching. We can set up the time and the date for the background job. And we can set up the parameters like the company, the matching method, and the period and fiscal year. Thus, a job can be scheduled in the background. So thus, by scheduling the jobs, the complete inter-company matching and reconciliation process can be automated. So these were the key learnings for this session. You see some additional learning sites available here for micro-learning. Thank you and stay tuned to the latest updates.