2 Feature Summary

This chapter describes the feature enhancements in this release.

Noteworthy Enhancements

This guide outlines the information you need to know about new or improved functionality in the AI Foundation Cloud Services application updates and describes any tasks you might need to perform for the update. Each section includes a brief description of the feature, the steps you need to take to enable or begin using the feature, any tips or considerations that you should keep in mind, and the resources available to help you.

Column Definitions

• Feature: Provides a description of the feature being delivered.

• Module Impacted: Identifies the module impacted associated with the feature, if any.

• Scale: Identifies the size of the feature. Options are:

  • Small: These UI or process-based features are typically comprised of minor field, validation, or program changes. Therefore, the potential impact to users is minimal.

  • Large: These UI or process-based features have more complex designs. Therefore, the potential impact to users is higher.

• Delivered: Is the new feature available for use immediately after upgrade or must the feature be enabled or configured? If no, the feature is non-disruptive to end users and action is required (detailed steps below) to make the feature ready to use.

• Customer Action Required: You must take action before these features can be used. These features are delivered disabled and you choose if and when to enable them.

Table 2-1 Noteworthy Enhancements

Feature	Module Impacted	Scale	Delivered	Customer Action Required?
Date range filters	Size Profiling	Small	Yes	No
Approval filters	Size Profiling	Small	Yes	No
Export process change	Size Profiling	Small	Yes	No
Queue run status	Size Profiling	Small	Yes	No
Generate higher level profiles button removed	Size Profiling	Medium	Yes	Eliminated need for manual runs and using a POM adhoc job process
Added size range descriptions	Size Profiling	Small	Yes	No
Adjusted ‘Submitted’ versus ‘Approved’	Size Profiling	Small	Yes	No
Improvements to scoring	Customer Decision Trees	Small	Yes	No
Job enhancements	Promotion, Markdown and Offer Optimization	Small	Yes	No
Time phased inventory planning	Inventory Optimization	Large	Yes	No
Truck scaling	Inventory Optimization	Large	Yes	No
Purchase Order / Transfer View	Inventory Optimization	Small	Yes	No
Trade-off Analysis	Inventory Optimization	Small	Yes	No

Size Profiling Cloud Service Enhancement

Approved By User Filter

A new filter, Approved by user, has been added. Initially when a user opens an approved profiles tab, it will be set to the logged in user and only profiles approved by the logged in user are displayed. The user will need to select any user name from the list and then apply the filter to see the profiles approved by other users. Auto-approved profiles can be viewed by selecting SPO_BATCH_USR from the drop down. (The option in the drop down will change to Auto Approved).

Approval Filters

A new filter, Approved by user, was added. Initially when a user opens an approved profiles tab, it is set to the logged in user and only profiles approved by the logged in user are displayed. The user will need to select any user name from the list and then apply the filter to see the profiles approved by other users. Auto-approved profiles can be viewed by selecting SPO_BATCH_USR from drop down. (in the August release the option in the drop down will change to Auto Approved.)

Export Process Changes

The export process, which is used to export the submitted profiles available in the system, has been modified to generate export file content only if there have been submitted profiles available from the last exported date.

‘In Queue’ Status for Runs

A new status for Runs has been introduced once runs are submitted. If a user submits a run and the execution has not yet started, the run will be in ‘In Queue’ status. The status will be changed to ‘In Progress’ when the run execution starts. The user cannot perform the view/edit operations on the run when it is in the ‘In Queue’ status; however it can be copied or deleted.

Generate Higher Level Profiles from Submitted Profiles Tab — Removed

The Generate Higher Level Profiles button is no longer available from the Submitted Profiles tab. This was used to generate submitted profiles from the front end. This is now performed using a POM AdHoc job process (On-Demand) or batch process that runs daily. The final outcome of the process can be seen in the Submitted Profiles tab once the job completes.

Size Range Description Column added to Size Ranges Data Grid

The Size Range Description column has been added to the Size Ranges data grid. At the time of creating a run, this enables the user to identify to which size range a size belongs. This is used while editing size ranges in bulk so that a user can filter the size ranges according to the value in this column.

Adjusted ‘Submitted’ versus ‘Approved’

The “Approve” and “Submit” labels have been switched to be better aligned with the terminology used in downstream applications in Merchandising and Planning. Labels are switched in all screens, actions, and filters. Submitted profiles are the ones that are internally reviewed and submitted within Profile Sciences. Approved profiles are the ones that are exported to other applications like Merchandising and Assortment and Item Planning. 

Customer Decision Tree Enhancements

Improvements to scoring

Improvements to Scoring of the Customer Decision Tree modeling have been added to support scoring larger tree sizes.

Promotional and Markdown Optimization Operational Enhancements

Job Enhancements

The following operational enhancements have been made:

• Performance of POM jobs associated with loading product hierarchy into AIF have been improved.

• Adhoc job for creating Offer Optimization batch runs has been added. It is called PRO_OPT_CREATE_RUNS_ADHOC.

• Modified the PMO_ACTIVITY_LOAD_JOB to not throw an error for weeks when either the sales or the inventory for that week is missing.

• Fixes for the RSE_INV_PR_LC_WK_PROCESS_JOB for RSE inventory load:

  • Performance of POM job for RSE inventory load has been improved.

  • Modified process to avoid using RI table statistics to identify which weeks to load.

  • Changed rse_proc_stat update process to not move last processed week unless the week contained a few records.

• Pro_season_curr_opt_metric job is no longer needed as markdown metrics (for example, last markdown, last markdown date) have been added to the RSE price cost ETL process. The process now uses the first receipt date to extract the price and new metrics.

• Performance of one of the data cursors used in PRO_OPT_JOB for optimization has been improved. This resulted in further reducing the time needed for optimization process.

Inventory Optimization Enhancements

Time Phased Inventory Plan

Time-Phased Inventory Plan: A time-phased inventory plan is generated using simulation and optimization techniques to determine the optimal projected values of purchase orders, transfers, expected wastage quantity, and so on for each review day in the configured horizon of up to 16 weeks. Supply chain attributes such as lead time, review frequency, and the supply chain network are combined with the demand forecast to determine inventory projections and the resulting inventory movements necessary to meet target inventory.

Note:

The time-phased plan can be viewed in the “more details” pop-up in the PO/Transfer tab. The documentation change is outlined below:

See the Oracle Retail Inventory Optimization Cloud Service User Guide for update 22.2.301.0.

Truck Scaling

Truck Scaling: Truck scaling is the process of reviewing and adjusting purchase orders so that truck capacity is maximized. The truck scaling process recommends scaled order quantities that maximize truck utilization while taking into account business rules. Truck scaling is performed automatically for every run, and the scaled quantity is shown in the table of the PO/Transfer view. The recalculate option in the same view rescales the quantities when the user overrides recommended order quantities.

See the Oracle Retail AI Foundation Cloud Service Implementation Guide for update 22.2.301.0.

PO/Transfer View

The table in the PO/Transfer view has been restructured to show the line items within each PO.

Trade-off Analysis

Trade-off analysis is the process that ultimately generates the trade-off curve that the user reviews to understand the inventory required to meet a given service level. The trade-off analysis now uses Machine learning, Simulation and Optimization techniques to evaluate the impact of different policies on key business metrics, namely inventory cost and lost revenue. The output of this analysis is used to recommend the initial replenishment policies for each item-location.