Machine Learning Algorithm - Load Balancing

[Karthik_7694]

Hello All,

I have an Use case scenario which needs to be solved using Machine Learning.

Use Case Scenario Description:

Consider a help desk Support Ticket Dataset which is available. We need to build a Machine Learning Model for assigning the support tickets to the help desk agents. The Tickets assigned to Help Desk agents should be like every day a minimum threshold and maximum threshold should be set to the help desk agents so that all the help desk agents will have equal amounts tickets assigned to them and not any one agent will need to work on more tickets so that there workload is also equal. It will be helpful if some one suggest me the correct algorithm for solving this use case and also the technical workflow.

[PhilippK]

Hi @Karthik_7694 ,

I would first ask myself whether you need a Machine Learning algorithm at all.

In case the support tickets already have a "category" (e.g. general IT support, MS Outlook Support, HR Support) and this assigned category is really valid, then you don't need machine learning anymore to predict its category.

In case your Help Desk Agents are already assigned to certain categories, then you don't need Machine Learning to predict which agent is the best fit.

For those cases, a simple rule-based distribution of support tickets to Help Desk agents is sufficient.

If the assumptions above are not correct -e.g. the support tickets are not assigned to a category yet-, then Machine Learning makes sense. In this example it would be a Classification Problem - here you find an overview about which algorithms are a potential fit:

You can find example workflows here:

In addition, I recommend our Data Science Learning Path for you, to learn more about it:
https://community.alteryx.com/t5/Learning-Paths/Data-Science-Learning-Path/ta-p/504157

Alternatively, you can leverage the Alteryx Designer Add-On "Intelligent Suite". With its "Assisted Modeling", you get a guide along your way to build a predictive model.

Let me know whether this is the solution you were looking for.

Best regards

Phil

[Karthik_7694]

Hi PhilippK ,

Thanks for your solution. The objective is to assign tickets to the help desk agents based on threshold. Assume the example dataset attributes.

Ticket Id	Unique Number
Description	Description about Ticket
Priority	Invoice Priotity - Sev1, Sev2, Sev3, Sev 4 (Critical Ticket that needs to be addressed immediately)
Created	Date on which the Ticket was created
Assigned to	Person who processed the Ticket
Resolved	Date at which the Ticket was processed
Assignment group (Target Variable)	Team Members to which the ticket needs to be allocated

First the ticket needs to be grouped based on severity and then the ticket needs to be routed to the help desk agents with the tickets being assgined equally to all based on the min threshold and max threshold.

Min Threshold - Minimum tickets that a help desk agent needs to resolve per day

Max Threshold - Maximum tickets that a help desk agent needs to get assigned per day

[PhilippK · Accepted solution]

Hi @Karthik_7694 ,

thanks for sharing this example.

In this case you don't need machine learning algorithms. A rule-based distribution of support tickets to Help Desk agents is sufficient. 

For example, you can leverage the TILE tool to distribute the tickets (click on "open example"):

 

Best regards

Phil