System and method for data-driven insight into stocking out-of-stock shelves
In various examples, a system identify a first issue object associated with the alert by making a first set of determinations, based on an alert of an active issue of a system resource. Additionally, the system can determine whether the active issue associated with the first issue object can be automatically corrected by one or more self-healing processes, based on the first issue object. Moreover, the system can implement the one or more self-healing processes, based on determining that the active issue associated with the first issue object can be automatically corrected by one or more self-healing processes.
1. A system comprising:
one or more processors; and
memory resource storing a set of instructions, that when executed by the one or more processors, cause the one or more processors to:
receive, from a database, a current shelf inventory of a product on a shelf in a store;
generate multiple forecasts of future sales by applying a plurality of machine learning models on a rate of sales model associated with the product;
select a single forecast from the multiple forecasts based on past performance of a machine learning model the plurality of machine learning models which generated the single forecast;
tune the machine learning model to avoid overfitting;
update inter-purchase times for the product based on updated sales data, the updated sales data including information indicating one or more instances at least one unit of the product was removed from the shelf;
update the rate of sales model based on the updated inter-purchase times; and
generate, based at least on the updated rate of sales model, a restocking schedule for the product.
2. The system of claim 1 , wherein execution of the set of instructions, by the one or more processors, further causes the one or more processors to:
transmit, to an autonomous vehicle, one or more instructions based on the restocking schedule, the one or more instructions causing the autonomous vehicle to implement one or more restocking operations to restock the product on the shelf.
3. The system of claim 1 , wherein execution of the set of instructions, by the one or more processors, further causes the one or more processors to:
transmit, to a computing device of a store associate, one or more restocking instructions based on the restocking schedule.
4. The system of claim 1 , wherein execution of the set of instructions, by the one or more processors, further causes the one or more processors to:
identify, within one of the rate of sales model and the updated rate of sales model, an amount of inventory corresponding to an apex rate of sales of the product.
5. The system of claim 4 , wherein generation of the restocking schedule for the product is further based on a threshold range of the amount of inventory corresponding to the apex rate of sales.
6. The system of claim 1 , wherein the machine learning model is updated on a periodic basis, the updates to the machine learning model being based on predictive ability of the machine learning model regarding sales of the product.
7. The system of claim 6 , wherein execution of the set of instructions, by the one or more processors, further causes the one or more processors to:
receive the updated sales data; and
modifying the current shelf inventory based on the updated sales data.
8. The system of claim 7 , wherein the modification of the current shelf inventory and the modifying of the rate of sales model occur in real-time after each sale of the product.
9. The system of claim 1 , wherein the rate of sales model identifies distinct rates of sales of the product when the shelf is full and when the shelf is half-full.
10. A computer-implemented method comprising:
receiving a current shelf inventory of a product on a shelf in a store;
generating multiple forecasts of future sales by applying a plurality of machine learning models on a rate of sales model associated with the product;
selecting a single forecast from the multiple forecasts based on past performance of a machine learning model the plurality of machine learning models which generated the single forecast;
tuning the machine learning model to avoid overfitting;
updating inter-purchase times for the product based on updated sales data, the updated sales data including information indicating one or more instances at least one unit of the product was removed from the shelf;
updating the rate of sales model based on the updated inter-purchase times; and
generating, based at least on the updated rate of sales model, a restocking schedule for the product.
11. The computer-implemented method of claim 10 , further comprising:
transmitting, to an autonomous vehicle, one or more instructions based on the restocking schedule, the one or more instructions causing the autonomous vehicle to implement one or more restocking operations to restock the product on the shelf.
12. The computer-implemented method of claim 10 , further comprising:
transmitting, to a computing device of a store associate, one or more restocking instructions based on the restocking schedule.
13. The computer-implemented method of claim 10 , further comprising:
identifying, within one of the rate of sales model and the updated rate of sales model, an amount of inventory corresponding to an apex rate of sales of the product.
14. The computer-implemented method of claim 13 , wherein generation of the restocking schedule for the product is further based on a threshold range of the amount of inventory corresponding to the apex rate of sales.
15. The computer-implemented method of claim 10 , wherein the machine learning model is updated on a periodic basis, the updates to the machine learning model being based on predictive ability of the machine learning model regarding sales of the product.
16. The computer-implemented method of claim 15 , further comprising:
receive the updated sales data; and
modifying the current shelf inventory based on the updated sales data.
17. The computer-implemented method of claim 16 , wherein the modification of the current shelf inventory and the modifying of the rate of sales model occur in real-time after each sale of the product.
18. The computer-implemented method of claim 10 , wherein the rate of sales model identifies distinct rates of sales of the product when the shelf is full and when the shelf is half-full.
19. A non-transitory computer-readable medium storing instructions, that when executed by one or more processors, causes the one or more processors to:
receive, from a database, a current shelf inventory of a product on a shelf in a store;
generate multiple forecasts of future sales by applying a plurality of machine learning models on a rate of sales model associated with the product;
select a single forecast from the multiple forecasts based on past performance of a machine learning model the plurality of machine learning models which generated the single forecast;
tune the machine learning model to avoid overfitting;
update inter-purchase times for the product based on updated sales data, the updated sales data including information indicating one or more instances at least one unit of the product was removed from the shelf;
update the rate of sales model based on the updated inter-purchase times; and
generate, based at least on the updated rate of sales model, a restocking schedule for the product.
20. The non-transitory computer-readable medium of claim 19 , wherein execution of the set of instructions, by the one or more processors, further causes the one or more processors to:
transmit, to an autonomous vehicle, one or more instructions based on the restocking schedule, the one or more instructions causing the autonomous vehicle to implement one or more restocking operations to restock the product on the shelf.