# Insights
You can use AWS Supply Chain Insights to generate inventory shortage and excess and lead time deviation insights based on the watchlist configured. Insights also provides recommendations on how to resolve the deviations. Insights scans for inventory and lead time risks every 24 hours or when new data is ingested into data lake.
**Note**
You can only view the current and projected inventory for products and locations that you are authorized to access.
**Topics**
+ [Insight settings](insight-settings.md)
+ [Viewing the network map](viewing-network-map.md)
+ [Viewing inventory visibility](viewing-inventory-visibility.md)
+ [Creating insight watchlist](creating-insights.md)
+ [Viewing inventory insights](viewing-inventory-insights.md)
+ [Resolving an inventory risk insight](resolving-insights.md)
+ [Lead time insights](resolving-lead-time-insights.md)
# Insight settings
After creating an instance, follow the procedure below:
1. In the left navigation pane on the AWS Supply Chain dashboard, choose the **Settings** icon. Choose **Organization** and then choose **Insights**.
The **Insight Settings** page appears.
![\[Updating Insights settings\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/insights_setttings.png)
1. Under **Projection Period**, enter the inventory projection time horizon and the time buckets. You can see inventory projections upto a total of six months.
**Note**
You can group and analyze the inventory projections in daily, weekly, or monthly intervals. Choosing a daily interval will provide a daily projection and weekly and monthly intervals will provide a long-term projection in a single bucket. Insights supports up to 60 days, 8 weeks, and 3 months per projection bucket.
The following example displays the projected inventory level for a portable air conditioner at the New York warehouse for 7 days, next 4 weeks, and 1 month beyond the weeks.
![\[Projection period example settings example\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/Insishts_settings_example.png)
1. Under **Rebalancing Recommendations Options**, you can setup the radius surrounding the stocked out site to search for available stock for rebalance. You can setup the distance in miles or kilometers.
You can configure the rebalance model to optimize inventory levels for both supplying and receiving sites. Insights supports up to a maximum of six weeks beyond the current date, and you can customize the time horizon by factoring your lead times to see the impact of the rebalance before and after transfers.
1. Under **Rebalancing Recommendations Score Weights**, use the **Up/down** arrow to enter the core weight values to determine how ranking is calculated for rebalance recommendations.
Depending on the inventory risk resolved, distance, time horizon, available transportation modes from the ingested data (transportation\$1lane.trans\$1mode), and shipping costs (transportation\$1lane.unit\$1costs), Insights recommends one or more ways to resolve an inventory risk insight. Insights also provides a *Score* per recommendation which is derived based on the weights configured. The higher the score, the recommendation is ranked higher and is displayed at the top.
+ *Distance* – Distance between your current location and the location where you want to transfer inventory from.
+ *Emissions (CO2)* – CO2 emissions computed for the rebalance option.
+ *Risk Resolved* – Net improvement in inventory risk percentage when excess inventory is reduced at one location to help restock the current stocked out location.
+ *Shipping Cost* – Shipping cost to rebalance and transfer inventory from one location to another.
# Viewing the network map
After ingesting the required datasets for Insights, the network map displays the current and projected inventory for products and locations in a map view for quick understanding of your inventory health and projected health. Locations appear in clusters, and the total number of locations appear under each cluster. You can zoom in on each cluster to see individual locations. Each icon represents a location type. The colored ring shows the inventory health for each location or cluster for the selected time interval on the scroll bar at the bottom left. Inventory health status depends on the inventory policy, that is, *min\$1safety\$1stock* and *max\$1safety\$1stock* in your ingested data.
The ring colors are defined as follows:
**Note**
The color code definitions remain the same throughout Insights.
+ **Red** – Products in this location are stocked out or are at risk of a stock out for future dates.
+ **Green** – Products in this location are well within your safety stock levels.
+ **Purple** – Products in this location have excess stock or are at risk of a holding more stock than your safety stock levels for this product and site.
To view the network map, perform the following procedure.
1. In the left navigation pane on the AWS Supply Chain dashboard, choose **Network Map**.
The **Network Map** page appears.
![\[Viewing the network map\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/insights_network_map.png)
1. Select a ring and zoom in on a location that you need. You can view the details of the current and projected inventory for one or more particular items.
1. Use the timeslider on the bottom left of the page to view the projected inventory for the current map view. The slider defaults to current date representing current inventory health.
1. Click the **\$1/-** symbol to zoom in and out of a particular location in the network map.
1. Click the **Filter** icon to filter by **Locations** and **Products**. Your permissions determine your level of access.
When you click on a cluster of sites, you will see a pop-up on the right side of the page, which displays the current inventory levels, safety stock levels for this product, and projected inventory graph.
# Viewing inventory visibility
You can use inventory visibility to view the inventory projections for all the ingested products and site combinations. You can change the projections view by product or location.
To view the inventory visibility, perform the following procedure.
1. In the left navigation pane on the AWS Supply Chain dashboard, choose **Inventory Visibility**.
![\[Inventory Visibility\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/inventory_visibility.png)
1. To know when the inventory visibility page was last updated, see **Date updated** on the top right corner of the page. The page is refreshed when you ingest data into data lake. By default, Insights are generated every 24 hours or when data is ingested into data lake.
1. Choose **Filters** to filter inventory projections based on *Products*, *Locations*, or *Inventory Risks*. Under **All Products**, you can select a group of products based on their product hierarchy, that are stored under the *product-hierarchy* data entity upto one level. Under **All Locations**, you can select a group of sites based on their regions, that are stored under the *geography* data entity upto one level.
Under **Inventory Risks - Current Day Locations**, select *Excess*, *Balanced*, or *Stock Out* to view projections with specific inventory risk for the current date.
1. Select the **Pivot by** dropdown to filter the inventory by **Location** or **Product**.
**Pivot by Location** – When you pivot by location, the inventory projections are grouped by location. At a high-level, for a given location, you can view the site type (for example, RDC, DC, and so on), number of products at the location, number of products that are balanced(that is, well within their safety stock range), number of products that are stocked out, and the number of products that are excess in stock.
![\[Inventory Visibility by location\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/pivot_by_location.png)
**Pivot by Product** – When you pivot by product, the projections are grouped by product. At a high-level, for a given product, you can view the category (that is, one level up), the total number of available products, the total number of products on order, and the total number of products currently in transit across locations.
![\[Inventory Visibility by product\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/pivot_by_product.png)
# Understanding inventory projections
This section explains how to read the inventory projections.
![\[Inventory projections\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/inventory_projections.png)
+ What is **On Hand** and **Safety stock?** – Displays the on-hand inventory value from the latest snapshot for both past dates and current date. This information is extracted from the *inv\$1level* data entity. When there are multiple records with different on-hand values for the same snapshot date, Insights will select the latest snapshot record for processing. The safety stock is the range specified in the inventory policy.
+ **How is demand calculated?** – Insights gathers data from the forecast, outbound sales orders, and the transfers orders (that is, products moving out of site for a given time frame) to calculate the total demand. When demand is available at a higher granularity, such as, weekly, monthly, and so on, Insights will spread the forecasted value across the given time frame.
+ **Prior** – When you slide the **Prior** button, you can view the inventory values for the last seven days, including any day in the past.
+ **How is **Projected** inventory different from **On Hand**?** – On hand inventory is the current stock in your ERP system and projected inventory is the future inventory level prediction based on factors such as previous day’s ending on hand/projected level, inbound supply (inbound order line, inbound shipment, inbound order line schedules), outbound sales (outbound order line, outbound shipment, and the demand forecast. Using projected inventory, you can plan the future inventory required to avoid stockouts or overpricing.
+ **How is **On Hand** different from **Projected On Hand?**** – Insights calculates projected on hand when there are no records available for the current date using the same logic used to calculate the projected inventory for future dates.
+ **How is quantity unit of measure (UOM) calculated and are there any defaults used?** – The unit for inventory quantity measures, such as on hand, on order, in transit, and projected inventory are displayed to distinguish between eaches, pallets, and cases. To prevent UOM mismatches and streamline calculations, Insights defaults to using the product’s base UOM specified in the product data entity for conversions. The unit conversions are derived from *product\$1uom* and *uom\$1conversion*. For more information on the data entities, see [Insights](entities-insights.md).
You can also set the default UOM by adjusting the default configuration. For more information on how to change the default configuration, see [Get support for AWS Supply Chain](admin-support-ug.md).
+ **Are inventory projections and risks generated for products that are not in stock?** – Adjust the inventory policy safety stock range to zero for products that are not in stock. This adjustment will prompt Insights to categorize such product-site combinations as products not in stock. Similarly, you will be alerted to excess stock risks when stock is held at a location. Insights also offers recommendations to move excess stock out and receive stock when there is a stock out.
**Note**
This feature is only available in US East (N. Virginia).
+ **How does Insights handle unallocated demand?** – When *outbound\$1shipment* information is unavailable, Insights will allocate demand from *outbound\$1order\$1line* to either the promised delivery date or the requested delivery date. When *outbound\$1shipment* information is available, Insights will distribute the total demand quantity across ship dates. Any unallocated demand in a day and up to six months are carry forwarded. When there is a cancellation, Insights will stop carrying forward the demand.
**Note**
This feature is only available in US East (N. Virginia).
# Creating insight watchlist
You can create an insight watchlist to track and notify you on supply chain risks and deviations.
1. In the left navigation pane on the AWS Supply Chain dashboard, choose **Insights**.
The **Insights** page appears.
1. If you are a first-time user, select an insight type to create an insight watchlist. See [Creating an inventory risk watchlist](#creating-risk-watchlist) and [Creating a lead time deviation watchlist](#creating-lead-time-watchlist).
To view existing watchlists, see [Viewing inventory insights](viewing-inventory-insights.md).
## Creating an inventory risk watchlist
You can create an inventory risk insight watchlist to view projected stock out and excess stock risks generated by Insights from the tracking parameters you selected.
![\[Inventory risk watchlist\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/insights_watchlist.png)
1. In the left navigation pane on the AWS Supply Chain dashboard, choose **Insights**.
The **Insights** page appears.
1. Choose **New Insight Watchlist**.
The **Create an Insight Watchlist** page appears.
1. Under **Select an insight type**, choose **Inventory Risk**.
1. Under **Name the watchlist**, enter a name to track your insight watchlist.
1. Under **Select location(s)**, select the locations from the drop-down that you want to add to your watchlist.
1. Under **Select product(s)**, select the products from the dropdown that you want to add to your watchlist.
1. Under **Tracking Parameters**, choose what you want to track. The options are Stock Out Risk, Excess Stock Risk, or Both.
1. Under **Time Horizon**, enter the time frame to generate inventory risk notifications.
1. Under **Watchers**, you can add other users who you think might benefit from this insight. The users within this insight can track and collaborate to resolve risks.
All the settings you chose are displayed on the right.
1. Choose **Save** to save and create an inventory risk watchlist.
## Creating a lead time deviation watchlist
You can view and receive notifications for lead time deviations that AWS Supply Chain discovers. You can select any insight, and AWS Supply Chain will recommend how to address it.
![\[Lead time deviation watchlist\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/leadtime_watchlist.png)
1. In the left navigation pane on the AWS Supply Chain dashboard, choose **Insights**.
The **Insights** page appears.
1. Choose **New Insight Watchlist**.
The **Create an Insight Watchlist** page appears.
1. Under **Select an insight type**, choose **Lead Time Deviation**.
1. Under **Name the watchlist**, enter a name to track your insight watchlist.
1. Under **Select location(s)**, select the locations from the drop-down to add to your watchlist.
1. Under **Select product(s)**, select the products from the drop-down to add to your watchlist.
1. Under **Tracking Parameters**, **Standard deviation**, select the lead time deviation percentage from the drop-down. When the percentage is met, AWS Supply Chain will generate an insight and notify you about the lead time deviation.
1. Under **Tracking Parameters**, **Historical time period to track miss frequency**, select the historical time period of your ingested data from the drop-down to analyze lead time deviations.
1. Under **Watchers**, you can add other users to collaborate and share the risks and notifications.
All the settings you chose are displayed on the right.
1. Choose **Save** to save and create an inventory risk watchlist.
**Note**
AWS Supply Chain only supports 1000 insights per watchlist and 100 watchlists per instance. To increase the limit, contact [AWS Support](admin-support-ug.md).
# Viewing inventory insights
When you create a watchlist for a specific product, site, risk type, and planning horizon, depending on the notifications settings, you will get notified when Insights detects an inventory risk. You will receive notifications through the web application or email. You can view the inventory risks in *Card* or *Table* view. By using the *Card* view, you can view the risks in a list format separated by when the risks will happen. For example, 0 to 7 days, 7 to 14 days, or 14\$1 days.
Using the *Table* view, you can view the risks by name of the product, the impacted site name, type of risk, risk in days, the percentage deviation from the relevant threshold, start of the on-hand value, the safety stock values you ingested under the *inv\$1policy* data entity for this product/site combination, and the inventory projections.
Choose the *chat* icon to collaborate with your peers on the inventory risk.
You can use the **Search** field to search the inventory insights page by product and site name.
Choose **Edit** on the top-right of the page to edit the inventory insights. For information on how to edit the insight watchlist page, see [Creating insight watchlist](creating-insights.md).
**Note**
AWS Supply Chain supports rebalance planning horizon for up to six weeks.
+ **New Insights** – This section displays all new insights that AWS Supply Chain discovers after you created your Insight Watchlist. AWS Supply Chain scans for Inventory Risk Insights every 6 hours, and Lead Time Insights every 24 hours.
+ **In Review** – This section displays all insights that are currently under review.
+ **Resolved** – This section displays resolved insights.
# Resolving an inventory risk insight
Insights recommends one or more ways to resolve an inventory risk depending on the distance, time horizon, available transportation modes in the ingested data (transportation\$1lane.trans\$1mode), shipping costs (transportation\$1lane.unit\$1costs), and emissions that you've configured under Insights settings. The recommendation might include an inventory transfer from other locations within a certain distance and this would resolve an inventory risk in the location under review.
Under **Settings** > **Insights**, **Rebalancing Recommendations Score Weights**, you can adjust the core weight values to determine how ranking is calculated for rebalance recommendations. You can setup the radius surrounding the stocked out site to search for available stock for rebalance. You can set the distance in miles and kilometers. You can configure the rebalance model to optimize inventory levels for both supplying and receiving sites. Insights supports up to a maximum of six weeks beyond the current date, and you can customize the time horizon by factoring your lead times to see the impact of the rebalance before and after transfers.
Inventory risk recommendations are helpful for immediately resolving stockout issues rather than overstocks. You may see rebalancing recommendations linked with overstock or excess stock issues but those will have a stockout risk at the receiving site.
1. In the left navigation pane on the AWS Supply Chain dashboard, choose **Insights**.
The **Insights** page appears.
1. Under **New Insights**, select an insight to resolve the inventory risk.
1. Choose **View details**.
An overview of the inventory risk with the current and projected inventory, and the rebalance options are displayed.
1. Under the details page, you can view the following:
+ *Identified* – Displays the date on when the inventory risk was identified.
+ *Product* – Displays the product in the inventory that is at risk.
+ *Destination* – Displays the destination where the product should be shipped.
+ *Risk Timeframe* – Displays the upcoming risk in days with the current inventory.
+ *Summary* – Displays the details of the risk in detail.
+ *Current inventory* – Displays the inventory that is currently on hand, the safety stock limit, and the allocated amount of inventory against the current orders.
+ *Projected Inventory* – Displays how your current inventory is projected starting daily to upto six weeks. Choose the **graph** icon to view the inventory in a graph.
1. Under **Rebalance Options**, review the rebalance options and choose **Select** against the rebalance option recommended by Insights.
Once you select the rebalance option, you can view the current and projected inventories before and after the rebalance.
1. On the **Confirm Resolution** page, the rebalance option that you chose is shown under **Resolution Option**.
1. Under **Message the team**, select the **After clicking...** check box to notify the team on the selected rebalance option.
1. Choose **Confirm**.
1. Choose **Send to Amazon S3** to export the resolution recommendation to your Amazon S3 bucket.
**Note**
Insights only recommends options to rebalance inventory. You must use your own planning system to update the inventory transfers or orders.
1. Choose the chat icon to collaborate with other users or add users as watchers to the current insight.
# Lead time insights
AWS Supply Chain provides insights on the lead time deviation for a vendor, product, and destination site level. The vendor lead time deviation insights also includes transportation mode, source locations, and identify lead time deviations at a more granular level. You can incorporate the recommended lead times in your planning cycle for enhanced planning accuracy and to avoid stock out risks.
For example, for supplier S, product P, destination site D, source site S, and transportation mode like Truck, Ship, and so on, the **Miss Frequency** displays the frequency of time the lead time was missed, compared to the planned lead time (that is, contractual lead times) shared in the vendor\$1lead\$1time entity. Therefore, Insights recommends to update the planned lead time for the same vendor, product, and site to avoid future lead time issues.
![\[Vendor lead time deviation\]](http://docs.aws.amazon.com/aws-supply-chain/latest/userguide/images/insights_leadtime_deviation.png)
Choose **Export All Recommendations** to export the vendor lead time recommendations for the ingested product, site, or vendor combinations in a .csv file into your Amazon S3 bucket. Once the export is completed, you will receive an email and notification on the AWS Supply Chain web application with a link to the Amazon S3 bucket where the recommendations are exported.
When values for optional columns *source\$1site\$1id* and *trans\$1mode* in the *vendor\$1lead\$1time* data entity are not available, Insights will use the master records for lead times. However, when transactional data for product, source site, destination site, vendor, and transportation mode is at a more granular level, that is, *inbound\$1order\$1line* and *inbound\$1shipment*, it influences the recommendations and the planned lead time. When there are multiple planned lead time records in the master data file, Insights will use the highest planned lead time for calculation.
# Lead time deviations and recommendations
For every generated lead time insight, you can select a row to view the historical trend on the vendor's performance on delivering products from a given ship location to the destination location.
For all orders that are in progress, you can view the status of the order and anticipate the delivery date. Insights uses a machine learning model trained on historical data spanning 1 to 5 years, a time frame chosen during the watchlist creation process, to provide predicted delivery dates with varying levels of confidence.
The **Historical Orders** graph displays the historical average lead times by month calculated from historical order data based on submitted and delivery dates. The bar graphs represent the current planned lead time value and the recommended lead time for vendors at specific sites for the given products. The actual lead time for future orders will be equal or lower than the recommended lead time 50% of the time.
The **Upcoming Orders** graph displays the future purchase order lead times by day, calculated by viewing the order’s submitted date and delivery dates. The bar graphs represent the current planned lead time value and the recommended lead time for vendors at specific sites for the given products. The actual lead time for future orders will be equal or lower than the recommended lead time 50% of the time.
The **Orders in Progress** table displays detailed information of the current or upcoming purchase orders that are at risk based on the model predictions from the historical data for the given vendor, product, and site. The table displays the granular view of all open orders with details such as order quantity, the expected or planned delivery date available from the order line data, and Insights predicted delivery dates with multiple options categorized as *Estimated - Low* and *Estimated - High*. The *deviation* determines the disparity between the estimated high dates and the actual delivery dates available at the order line level.
**Note**
The x-axis in the Historical Orders chart shows months according to the UTC timezone regardless of your location. This means that the beginning of the month coincides with 00h:00m:00s UTC of the first day of the month and the end of the month coincides with 23h:59m:59s UTC of the last day of the month.