Automation platforms aim to automate repetitive tasks using workflows, which
start with a trigger and then perform a series of actions. However, with many
possible actions, the user has to search for the desired action at each step,
which hinders the speed of flow development. We propose a personalized
transformer model that recommends the next item at each step. This
personalization is learned end-to-end from user statistics that are available
at inference time. We evaluated our model on workflows from Power Automate
users and show that personalization improves top-1 accuracy by 22%. For new
users, our model performs similar to a model trained without personalization.
Description
Personalized action suggestions in low-code automation platforms
%0 Generic
%1 gupta2023personalized
%A Gupta, Saksham
%A Verbruggen, Gust
%A Singh, Mukul
%A Gulwani, Sumit
%A Le, Vu
%D 2023
%K autiomation low-code
%T Personalized action suggestions in low-code automation platforms
%U http://arxiv.org/abs/2305.10530
%X Automation platforms aim to automate repetitive tasks using workflows, which
start with a trigger and then perform a series of actions. However, with many
possible actions, the user has to search for the desired action at each step,
which hinders the speed of flow development. We propose a personalized
transformer model that recommends the next item at each step. This
personalization is learned end-to-end from user statistics that are available
at inference time. We evaluated our model on workflows from Power Automate
users and show that personalization improves top-1 accuracy by 22%. For new
users, our model performs similar to a model trained without personalization.
@misc{gupta2023personalized,
abstract = {Automation platforms aim to automate repetitive tasks using workflows, which
start with a trigger and then perform a series of actions. However, with many
possible actions, the user has to search for the desired action at each step,
which hinders the speed of flow development. We propose a personalized
transformer model that recommends the next item at each step. This
personalization is learned end-to-end from user statistics that are available
at inference time. We evaluated our model on workflows from Power Automate
users and show that personalization improves top-1 accuracy by 22%. For new
users, our model performs similar to a model trained without personalization.},
added-at = {2023-06-26T07:03:37.000+0200},
author = {Gupta, Saksham and Verbruggen, Gust and Singh, Mukul and Gulwani, Sumit and Le, Vu},
biburl = {https://www.bibsonomy.org/bibtex/22333eb3c6f7c1d9cb30c31d790cf4f5b/amitpuri},
description = {Personalized action suggestions in low-code automation platforms},
interhash = {ecf406e9f4e430522d118ce547f71cc0},
intrahash = {2333eb3c6f7c1d9cb30c31d790cf4f5b},
keywords = {autiomation low-code},
note = {cite arxiv:2305.10530Comment: 4 pages, Accepted at ICSE 2023},
timestamp = {2023-11-25T14:20:16.000+0100},
title = {Personalized action suggestions in low-code automation platforms},
url = {http://arxiv.org/abs/2305.10530},
year = 2023
}