# Data entities and columns used in AWS Supply Chain This chapter describes the data entities and columns supported by each AWS Supply Chain module. **Note** The data entities listed in this chapter are required for each AWS Supply Chain module. For data entities required for Data Lake ingestion, see [Data entities supported in AWS Supply Chain](data-model-asc.md). **Topics** + [Sustainability](entities-sustainability.md) + [N-Tier Visibility](entities-n-tier.md) + [Supply Planning](entities-supply-planning.md) + [Insights](entities-insights.md) + [Order Planning and Tracking](entities-work-order-insights.md) + [Demand Planning](required_entities.md) # Sustainability The table below list the data entities and columns used by Sustainability for partner invitations and onboarding. **Note** **How to read the table:** **Required** – The column name is mandatory in your dataset and you must populate the column name with values. **Optional** – The column name is optional. For enhanced feature output, it is recommended to add the column name with values. **Not required** – Data entity not required. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/entities-sustainability.html) # N-Tier Visibility The table below list the data entities and columns used by N-Tier Visibility. **Note** **How to read the table:** **Required** – The column name is mandatory in your dataset and you must populate the column name with values. **Optional** – The column name is optional. For enhanced feature output, it is recommended to add the column name with values. **Not required** – Data entity not required. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/entities-n-tier.html) # Supply Planning The table below list the data entities and columns used by Supply Planning. **Note** **How to read the table:** **Required** – The column name is mandatory in your dataset and you must populate the column name with values. **Optional** – The column name is optional. For enhanced feature output, it is recommended to add the column name with values. **Not required** – Data entity not required. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/entities-supply-planning.html) # Insights The table below list the data entities and columns used by Insights for the Inventory Visibility, Network Map, Inventory Insights, and Rebalance Recommendations features. See the table below on how each feature in Insights uses the data entities. **Note** **How to read the table:** **Required** – The column name is mandatory in your dataset and you must populate the column name with values. **Optional** – The column name is optional. For enhanced feature output, it is recommended to add the column name with values. **Not required** – Data entity not required. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/entities-insights.html) # Order Planning and Tracking **Note** To generate an order insight, in addition to ingesting the required data entities and columns, you must configure your milestone and process definitions. For more information on configuring orders, see [Configuring Order Planning and Tracking for the first time](setting-up-work-orders.md). The table below lists the required data entities and columns to generate a order planning and tracking process. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/entities-work-order-insights.html) The following table describes the data entities that are *not* required to generate order planning and tracking. If these data entities are included in your dataset, the required columns are listed in the table below. [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/entities-work-order-insights.html) # Demand Planning The following table lists the data entities and columns used by Demand Planning. **How to read the table:** + **Required** – The columns in this data entity are mandatory to execute a demand forecast without any failures. + **Conditionally required** – The columns in this data entity are required depending on the configurations set under demand plan settings. For more information, see [Manage Demand Plan settings](settings.md). + **Recommended for forecast quality** – The columns in this data entity are required for the quality for the forecast. + **Optional** – The column name is optional. For enhanced feature output, it is recommended to add the column name with values. # Prequisites before uploading your dataset To successfully generate a forecast, make sure your dataset adheres to the following. + At least one *product\$1id* has a sales history of at least four times the forecast time horizon provided in the *outbound\$1order\$1line* dataset. For example, if the forecast time horizon is 26 weeks, the minimum order data requirement is 26\$14 = 104 weeks. + *Product\$1id* under the product data entity should not contain any incomplete data (null or empty string) or duplicates. + All the additional columns selected for granularity in the forecast configuration (that are *conditionally required* ‘) does not contain incomplete data (null or empty string). + The column *id* across all data entities (for example, product\$1id, site\$1id, ship\$1from\$1site\$1id) does not contain special characters, such as asterisk (\$1) and double quotes (" "). + The *order\$1date* does not contain invalid date. For example, 2/29/2023, that is 29th February 2023 is only valid on a leap year. To improve forecast accuracy, Demand Planning highly recommends the following. + Upload two to three years of outbound order line history as input to generate an accurate forecast. This duration allows the forecasting models to capture your business cycles and ensure a more robust and reliable prediction. + For improved forecast accuracy, it is also recommended to include product attributes such as *brand*, *color*, *product\$1group\$1id*, *product\$1introduction\$1day* and *discontinue\$1day* in the product data entity. + You can provide additional demand drivers information through the *supplementary\$1time\$1series* data entity. Note, only numerical values are supported. + You provide alternate product mapping when you have similar products or previous version for a new product. + Remove any non-recurring or one-time event such as COVID before uploading the historical sales data. # Data mapping example for fulfillment Below is an example to map brick and mortar or online sales to outbound order line dataset and optimize the historical demand setup. Use this example to structure your data for accurate forecasting. Review the configurations in this example to make sure your forecasting models capture the different fulfillment scenarios. **Note** If the data fields *ship\$1from\$1site\$1id*, *ship\$1to\$1site\$1id*, and *channel\$1id* are selected for forecast granularity, make sure they have values or enter *NULL* as the value. The forecast will fail if the fields are blank. | Data field | Description | Scenario 1 – Store sales (POS) | Scenario 2 – E-commerce demand fulfilled by store | Scenario 3 – E-commerce demand fulfilled by online fulfillment center (direct to customer) | | --- | --- | --- | --- | --- | | ship\$1from\$1site\$1id | Site at which inventory is managed | Store ID | Store ID | Fulfillment Center ID | | ship\$1to\$1site\$1id | Site that received the order | Enter NULL to avoid forecast failure | Country, Region, State, or Zip – as applicable | External retailer sore ID, or Country, Region, State, or Zip – as applicable | | channel\$1id | Map how an item is sold | Brick and mortar | E-commerce | E-commerce | [\[See the AWS documentation website for more details\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/required_entities.html)