Tiponomics: Analytics for Waiters
A recent lunchtime conversation with a friend reminded me that data-mining/analytics/optimization opportunities are lurking everywhere.
It all started innocently enough. I miscalculated the tip at lunch and was about to leave a 10% tip (rather than the 20% that I was planning to) when my friend pointed out the error. He said that he had been sensitized to tip amounts by his college-age son who had done part-time/summer jobs as a restaurant waiter for several years. He went on to share fascinating examples of how his son made real-time decisions to maximize his tips.
I don’t know if waiters everywhere think this way, but my friend’s son (let’s call him Chuck) seems to have a great knack for “tiponomics”.
“These four old ladies walked in. They didn’t order any drinks. From past experience, I knew they wouldn’t be in a hurry to leave. They will occupy one of my four tables for several hours, have a small total check, and I will be lucky to get a 15% tip. I am not going to spend my time waiting on them hand and foot.”
“These two guys in suits walked in. They started off with some expensive drinks. It was clear that they were on an expense account. Also, I knew they would’t be sitting around for ever. If I really waited on them and responded quickly to every request, I knew I’d get a fat tip. So that’s where I will spend my time.”
Pretty savvy, eh?
Let’s look at this through an analytics lens.
The key decision for Chuck to make is to decide how to allocate his time and attention across tables. The objective he is trying to maximize is the total tip amount over the duration of his shift. This is determined by the number of parties that come in to dine and the tip amount from each party. The latter, in turn, is the product of the check amount and the tip %.
The number of parties that come in to dine is obviously not in Chuck’s control. But if he can “turn over” his tables more, he can serve more guests and increase his tips per shift. It is not clear to me how he can increase his table turnover short of forcing guests to leave early (which, of course, will have dire consequences for Chuck sooner or later).
The check amount is driven by the number of people in that group, whether they order drinks or not, and what else they order. While the size of the group is clearly not in Chuck’s control, he can clearly affect the order by up-selling (e.g., the gratinati isn’t bad but I’d recommend the pasta stefano) and cross-selling (e.g., wine XYZ goes really well with this entree, a raita goes very well with this biriyani). In any event, since the up and cross-selling doesn’t add much time to taking the group’s order, there’s no time allocation decision to make – Chuck may as well do it.
The tip % is more interesting. Clearly, the more attentive and responsive Chuck is, the higher the tip %. But for the same dining experience, certain guest types may tend to tip more, others less. By data-mining historical data (“remembering past experience”), Chuck can take one look at the group and classify them as 10%/15%/25% tippers.
So can we put all this together (“Chuck’s Tips” 
) to help a new waiter hit the ground running?
- When you take the guests’ orders, suggest up-sells and cross-sells. In the beginning, get ideas for what to suggest from more experienced waiters. As your “database” grows (see below), use your own experience to produce effective suggestions.
- Once the order is complete, estimate what the check amount will be.
- From what you have seen and heard so far, classify the guest group as 10%/15%/25% tippers. Again, in the beginning, get ideas for how to classify from more experienced waiters. As your “database” grows, use your own experience.
- Multiply (2) and (3) to come up with “an expected tip amount” from each group.
- Order all your current guest groups from high to low and focus your attention on the top few groups on the list.
- When a new group walks in, calculate their expected tip amount (as in 1-4), insert them into the sorted list and focus your attention accordingly.
IMPORTANT: After every session, add to your “database”
- which up-sell and cross-sell suggestions worked and which didn’t, in the context of the customer type
- the outcomes for each dining group (both the check amount and the tip %) as well as any interesting explanatory variables that may be linked to these outcomes (e.g., businessmen in suits, Indian-American vegetarian teetotaler family , five old ladies) so that your guesses become better with time.
Bon Appetit!
July 20th, 2010 at 2:51 pm
Interesting read!
Other possible positive correlations with the tip amount….
Level of inebriation (there is probably an optimal amount of drunkenness from a tipping perspective)
Is the person “out to impress” the guests they are with….like on a date!
Possible negative correlations – Transient One-timer e.g., somebody passing through your town…maybe mapping to license plate data will provide that info.
July 20th, 2010 at 3:07 pm
@Satish: I like your list of unusual explanatory variables for the data-mining. Not sure I agree that a transient one-timer will necessarily give a small tip. I do agree, however, that the waiter shouldn’t “invest” in superb service since he won’t be able recoup the investment.
Thanks for your comment!
July 21st, 2010 at 3:33 pm
Great read!
Since a major portion of a waiter’s income comes from tips it behooves them to be acutely aware of the potential of the revenue stream from a customer.
A few thoughts:
If a waiter (pre)judges a customer as a ‘low paying prospect’ and proceeds to give them less than satisfactory service, can this sometimes lead to a ‘self fulfilling prophecy”?
A transient one-timer could be a good prospect for tips as the waiter has the opportunity to relieve the boredom or loneliness of the customer and connect with him or her in some way.
When one knows he is going to stay in a particular place for a few days, it pays to tip well the first time, to increase the chances of good service throughout the stay (I used to do this on my official trips , with consistently good results).
July 21st, 2010 at 9:59 pm
@Kasthuri,
> If a waiter (pre)judges a customer as a ‘low paying prospect’ and proceeds to give them less than satisfactory service, can this sometimes lead to a ’self fulfilling prophecy”? <
Good point – I am sure it can happen. However, the analytic approach hopefully gives a statistical edge that, over numerous guests and shifts, increases the expected tip payoff for the waiter, even if it leads to worse outcomes in a few cases.
Thanks!
July 22nd, 2010 at 1:25 pm
Rama,
I agreee that an accumulated analytical ‘wisdom’ will definitely increase the expected tip payoff.
Interestingly, I was one of the “Indian-American vegetarian teetotaler family” in a Thai restuarant. and the waiteress seems to have done some ‘analysis’ on the expected tip amount. We got a very cursory service and I met her expectations
July 23rd, 2010 at 2:23 pm
Nice!!
August 11th, 2010 at 10:10 am
Guys, how about that problem I found. That’s a competition in road traffic prediction. Is it solvable? What do you think?:
http://tunedit.org/challenge/IEEE-ICDM-2010
August 12th, 2010 at 6:35 am
It is solvable. ClearFlow, developed by Microsoft Research, uses machine-learning to predict traffic congestion. See http://nyti.ms/9IuJBM.
October 6th, 2010 at 10:40 pm
Rama,
It appears similar to planning everyday lunch menu for a family with WIDE needs. Diabetic, Geriatric, Non-Gastric, Low-Cholestral, kids-friendly,… the list is too long. I wish I am able to work out some “Cookanomics” like this.
November 1st, 2010 at 2:41 pm
the next time you go to your regular restaurant, you should write the url to this piece on the back of the receipt and invite comments from waiters.
i wouldn’t be surprised if there is a “human” dimension to this problem. after all, waiters are in a business where they are routinely treated as necessary annoyances; the few that treat them with some humanity probably earn better service (and, as a result, leave a bigger tip). haven’t you wondered why in some restaurants the staff is taught to open with “hi, my name is debbie and i will be your waitress today”?
November 1st, 2010 at 4:37 pm
Agreed. Like in most “analytically framed” problems, there is a human dimension, I am sure.
> the few that treat them with some humanity probably earn better service (and, as a result, leave a bigger tip
I have seen that, and strangely, I have seen the opposite too. When I try hard to be extra-nice to the waiter, I find that sometimes he/she begin to take me and my family for granted. Conversely, when I am sort of distant (but not rude), I find that I get better service. The human dimension strikes again, I guess.
December 21st, 2010 at 3:24 pm
@Sriram: Re: your idea of a privacy-supporting “universal” shopping identifier – see http://www.myreceipts.com, a promising startup with pilots in place with Whole Foods, Best Buy, Amazon.com and others. The attraction is of that its an entirely opt-in process, so you automatically solve the motivational issue. The downside is coverage – it will become truly useful only if it gains widespread acceptance. Rama, nice to see you back on the blogging saddle!
December 21st, 2010 at 5:15 pm
Sharron, Thanks for the link.