Andrew Ho

EECS Department, University of California, Berkeley

Technical Report No. UCB/EECS-2015-118

May 15, 2015

http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-118.pdf

Abstract Restaurant owners strive to save as much cost as possible to monetize their business. They emphasize labor cost as the major component in their overall cost structure. However, after our observations for a couple of weeks, we discovered a surprising fact: In many restaurants, there is always a constant number of staff throughout the day. Yet the number of customers coming in fluctuate greatly with time. For example, there are on average two transactions made per minute at La Vals, the pizza place, around 12pm, while there is only one transaction made in three minutes at 3pm. Number of staff, however, remains eight at any time in the day. In other words, restaurant owners are either over or under staffed most of the time. While labor cost is a burden for all restaurants but surprisingly, nobody is solving this problem. That’s why our capstone project is important. We are here to tackle staffing problem for restaurant so they would be able to focus wholeheartedly on making fantastic food. Our projects, if implemented successfully, would revolutionize how restaurant owners make staffing decisions. Our capstone team helps restaurants reduce labor cost by generating a dynamic staffing schedule for them. We do that by training our software to predict how many people will visit at a specific time during the week, and match that to how many staff the restaurant should hire at that shift. By leveraging our data driven service, staffing will become more efficient. Furthermore, we added behavior-modeling analysis, which would potentially generate better match between restaurants and staff. Our vision is to empower small business with technology so that they make the best decision for themselves. We believe everyone deserves to benefit from data to optimize their business with ease.

Advisors: Donald Wroblewski

---

BibTeX citation:

@mastersthesis{Ho:EECS-2015-118,
    Author= {Ho, Andrew},
    Title= {Discover Insights from Data Analysis},
    School= {EECS Department, University of California, Berkeley},
    Year= {2015},
    Month= {May},
    Url= {http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-118.html},
    Number= {UCB/EECS-2015-118},
    Abstract= {Abstract
Restaurant owners strive to save as much cost as possible to monetize their
business. They emphasize labor cost as the major component in their overall cost structure. However, after our observations for a couple of weeks, we discovered a surprising fact: In many restaurants, there is always a constant number of staff throughout the day. Yet the number of customers coming in fluctuate greatly with time.
For example, there are on average two transactions made per minute at La Vals, the pizza place, around 12pm, while there is only one transaction made in three minutes at 3pm. Number of staff, however, remains eight at any time in the day. In other words, restaurant owners are either over or under staffed most of the time. While labor cost is a burden for all restaurants but surprisingly, nobody is solving this problem. That’s why our capstone project is important. We are here to tackle staffing problem for restaurant so they would be able to focus wholeheartedly on making fantastic food. Our projects, if implemented successfully, would revolutionize how restaurant owners make staffing
decisions. Our capstone team helps restaurants reduce labor cost by generating a dynamic staffing schedule for them. We do that by training our software to predict how many people will visit at a specific time during the week, and match that to how many staff the restaurant should hire at that shift. By leveraging our data driven service, staffing will become more efficient. Furthermore, we added behavior-modeling analysis, which would potentially generate better match between restaurants and staff. Our vision is to empower small business with technology so that they make the best decision for themselves. We believe everyone deserves to benefit from data to optimize their business with ease.},
}

EndNote citation:

%0 Thesis
%A Ho, Andrew 
%T Discover Insights from Data Analysis
%I EECS Department, University of California, Berkeley
%D 2015
%8 May 15
%@ UCB/EECS-2015-118
%U http://www2.eecs.berkeley.edu/Pubs/TechRpts/2015/EECS-2015-118.html
%F Ho:EECS-2015-118