Strategies to reduce your food waste

According to a report from the Food and Agricultural Organisation (FAO), global food wastage per year is approximately 1.3 billion tonnes, which is roughly a third of the food produced in the world for human consumption. On a more local scale, waste in UK restaurants is approximately 1.6 million tonnes per year with around 600,000 tonnes of this being food. Breaking this down: 30% is from plate waste (customer leftovers); 5% from spoilage; 65% from prep waste (food not used after preparation).

Why exactly is this such a problem? Firstly, global population is on the increase with 10 billion people expected by around 2050. Therefore demand will be significant and without an increase in supply prices will rise. Added to this, climate change has the potential to create further difficulties in food production as extreme weather events such as droughts and floods will lower crop yields. Together, these issues could have disastrous consequences on food security leaving millions starving.Attempting to address this problem may seem daunting however, there are strategies restaurants can implement to contribute to reducing food waste.

1.Utilise preparation waste for the creation of other menu items. For example, SiloBrighton utilises broccoli cores in the creation of one of its dishes.

 

2) Offer a greater range of portion sizes or encourage the use of doggy bags for your customers.

3) Calculate and monitor your “actual wastage” with the help of vigilant stocktaking. For example, by connecting menu items with their ingredients i.e. the cheese burger needs 1 beef patty, 2 buns, a slice of cheese and pickle etc. When you take the dishes sold and multiply this by the recipes of each menu item you get the “theoretical usage”. When you do the stock count you can work out the “actual usage”. Minus the “theoretical usage” from the “actual usage” and you get “actual wastage”.

For simplicity:
Theoretical usage = Total dishes sold x individual recipe items
Actual usage = Ordered food items — remaining food items
Actual wastage = Actual usage — theoretical usage

The difference between the theoretical usage and actual usage will typically come down to:

  1. Portion sizes being bigger/smaller than defined in the recipe. More training of the kitchen team can help improve this.
  2. Items that are free and therefore not entered in the till (eg: staff meals or deliveries from third parties). To be able to identify the cause of the waste, it’s important to make sure that these are entered in the till and discounted to zero so that they are counted as part of the theoretical usage.

4) Buy and prep the right amount of food each day. This may seem like an obvious point to make but it is actually a very difficult task to get right. This is because there are a large number of variables which will affect your sales for any given day for example seasonal variations, overall growth trends as well as local weather and events.

Technologies are now available to accurately forecast sales, from the store level right down to the individual item level taking into account the previously mentioned variables. Tenzo has this capability by utilising cutting edge machine learning algorithms (or artificial intelligence). This technology has a proven track record of reducing food waste. Click here for more information and if you’re interested in a demo you can sign up here.

 

At an individual level these contributions are quite small, however, collectively (across all restaurants) they are huge and can have a significant effect on food prices and sustainability. For inspiration, here is a list of the most sustainable restaurants in the UK. Have a look — you may get some great ideas!

To learn more about reducing your restaurants’ food waste visit the Too Good to Waste Campaign run by the Sustainable Restaurant Association.

Why monitoring your reviews online matters?

It is something every restaurateur knows: good reviews boost takings while terrible ones can close you down. And, in an age when everyone can be an online critic, ratings have never been more important.

Work by two economists at the University of California, Michael Anderson and Jeremy Magruder, aimed to measure the relationship between online star ratings and customers’ purchasing decisions.

They found that a restaurant with a rating improved by just half a star (on a scale of 1 to 5) was much more likely to be full at peak dining times.

 

This was further backed up by Michael Luca, who published research in 2016, and found that a one-star increase in Yelp rating leads to a 5–9 percent increase in revenue.

Importantly, the two economists found that the increase in trade happened without any change in prices or the quality of food and service, confirming that it was the reviews that brought in the new customers.

The economists conceded that, while restaurants with strong reviews on the site did better business than poorly reviewed restaurants, establishing cause and effect was difficult.

“After all, restaurants that get good reviews are those that appeal to consumers and they would probably do well even in the absence of any reviews,” the pair write. However, they are confident the research is robust. They note that, when Yelp computes a business’s average rating (which ranges from 1 to 5 stars), it rounds off to the nearest half-star.

 

So, two restaurants that have similar average ratings can actually appear to be of very different quality to online viewers. For example, a restaurant with an average rating of 3.74 displays a 3.5-star average rating, while a restaurant with an average rating of 3.76 displays a 4-star average rating.

This, the economists claim, allows them to make important comparisons between restaurants that have different ratings — for example, 4 stars versus 3.5 stars — but are of nearly identical quality (for example, a 3.76 average versus a 3.74 average). Their conclusion? That half a star makes all the difference.

Furthermore, they found that the effect was more profound when alternative information was hard to come by, opening up the possibility that invented reviews could boost fortunes.

The pair write: “These returns suggest that restaurateurs face incentives to leave fake reviews, but a rich set of robustness checks confirm that restaurants do not manipulate ratings in a confounding, discontinuous manner.”

So what can you do about it?

We believe that there are 4 key steps to turning around social media performance.

  1. Inspect the data
  2. Incentivise your staff
  3. Be proactive and respond
  4. Address root causes

Inspect the data

To quote Louis Gerstner, ex-CEO of IBM :

“You don’t get what you expect, you get what you inspect”

… and the same is definitely true of social media scores.

Can you answer the following questions:

  • Which was my top performing store on social media this month?
  • How many likes do I get for an average post on Facebook and how did this month compare?
  • Do I have any critical reviews outstanding that I need to respond to?

If you can’t answer them within a minute or two — you need to work on your tools. Whether you invest in a solution to aggregate reviews for you, or have someone collate a regular report — you need to understand this data in some detail.

Incentivise your staff

Just making sure managers are aware of social media reviews will help — but there’s nothing quite like making social media scores part of an employee scorecard to help drive positive reviews. We’ve seen customers include an average review metric as 10% of a balanced scorecard impacting bonus at the end of each month. Of course, go to far and you could start seeing odd behaviours — an employee may push customers to make reviews — so use in moderation.

You can also run competitions, or have a “mention of the week” type award to rewards one-off performance.

Lastly, it’s important to role model the behaviors you want to see — make social media scores a topic at team meetings, and an important part of the day to day.

Be proactive and respond

 

Don’t just let negative reviews sit there — make sure you’re responding to them, and trying to remedy the situation. Customers are looking at the responses and well, and want to see an engaged restaurant.

Best in class restaurants can respond within a couple of hours — and it shows you’re thinking customer first. It’ll also help you get closer to the pulse of customer feedback.

Address root causes

Of course, you also need to listen to the content of customer feedback. Not all of it can be fixed with a staff incentive or by listening more closely.

Example of structural issues may be things like poor menu selection for vegetarians, or long wait times on certain days. Each of these comes with an obvious action that you can then decide to make if the reviews persist. Listening closely will help give you this feedback.

If you’d like to see how Tenzo can help you power all of the above — please get in touch for a demo.

How to get value from your restaurant data warehouse

Here at Tenzo we think a lot about data, how to create value from data, and what that means for the IT architecture of our different clients.

 
3As of Restaurant Data

We use our “3A” framework to think about a broad data approach:

  • Absorb: This is the process of getting all of your data into one place. It may include POS data, labor data, social data, inventory data, customer data, compliance data, IoT data, the list goes on. Importantly, you need to have both a process for loading the data, and then somewhere to put it.
  • Analyze: Now you’ve got your data, you need to extract insights. This ranges from simple alerts and exception reporting, to advanced analytical topics that might involve machine learning and A.I.
  • Act: Finally — the hard part — now you have to get someone to do something with the insights you have.

Let’s talk through each in more detail.

1. Absorb

In today’s world, we’re going to assume that you are comfortable working in the cloud. Of course, you could opt to store your data on premise — but you don’t need the hassle of maintaining architecture, and with AWS, Google Cloud and Microsoft Azure so prevalent — we’d recommend you start there.

Then you need to decide exactly to store your databases, as an example, you could choose:

  • Traditional SQL database e.g., MySQL, PostgreSQL, Microsoft SQL Server
  • NoSQL e.g., MongoDB, Cassandra etc.
  • Some hybrid approach e.g., Google BigQuery, or a combination of SQL and NoSQL

Our advice would be to choose a data store to match the kind of data you’re importing. For example, transaction and labor data is inherently very transactional (and thus lends itself to SQL), whereas IoT or customer feedback data may lend itself more towards a NoSQL type approach.

Having chosen somewhere to put the data — you then have to think about how to ingest it. For this, you’re going to have to build relationships with all of the people who store your data and then figure out how to get the data. Typically, this can be a combination of:

  • Using a public API
  • Streaming data live from stores; using custom code if needed
  • Daily dumps of data from vendors’ servers

Importantly, you have to build an understanding of the data you’re ingesting to make sure it’s accurate.

Now you have a choice: build vs. buy?

As a small player, the answer is easy… you won’t have the scale to cover the cost of building yourself. However — we also think that even at larger scales you should buy as long as your partner is open. It can be considerable effort an expense to own and maintain a data warehouse, and of course this doesn’t include the tremendous cost of creating that infrastructure.

Note: a common misconception is that you need to own the data warehouse to give you the depth of analysis you need. This just isn’t true if you have an open provider (yes — at Tenzo, we are!)

 
Analysis time!

2. Analyze

Ok — so now you’ve gotten all of your data in one place, what on earth do you do with it?

We like to categorize this in to 3 key areas:

a) Use alerts and exception reporting to catch the low-hanging fruit

First, you need to identify places that you want to catch obvious problems e.g.,

  • A significant year-on-year drop for a given location
  • Low inventory for a specific item
  • Potential incidents of fraud at the employee level
  • Respond to poor customer feedback and reviews

b) Dive one level deeper to fine tune the machine

Now it’s time to think about fine tuning your operating machine e.g.,

  • Optimizing daily labor schedules to match to demand
  • Trimming opening hours when needed
  • De-listing low performing items
  • Building team schedules that work well together
  • Identify the meaning behind customer feedback (understand sentiment around specific issues etc.)
 
What is A.I. and how is it relevant to me?

c) Now what on earth is “A.I.” and how is that relevant to me?

So, we all hear about A.I. and machine learning — but isn’t that just relevant at Google (playing Go) or for Uber and driverless cars ?

Well — actually, it can be used in restaurants too. In simple terms, A.I. allows computers to learn. That means they can recognize patterns outside of normal statistics (e.g., correlations and regressions), and ultimately start making decisions.

Some examples of where we see the potential for A.I. to be used in restaurants include:

  • Advanced forecasting (e.g., including weather and events) to aid prep, procurement and staffing
  • Shift planning and team selection to optimize sales
  • Fraud detection
  • Optimized digital signage and improved kiosk up-sell
  • Predictive maintenance and compliance schedules
  • Real-estate purchase and location selection
  • Dynamic promotion and pricing decisions
  • Talent identification and on-boarding

So— should you build this yourself, or look to a partner? At a very small level (1–2 locations) you may do much of this yourself, but as you hit 2–100 locations you’re going to start to want something that thinks about this on your behalf.

Above 100 locations and, while you might have an in-house capability for basic business insight, you need to assess whether you’ll have a leading data-science capability. As already discussed — incase you still want to the ability to run custom analytics, it helps to connect to an open platform— you need to be able to get your data out to talk to other systems.

At Tenzo, we’ll help you connect to other systems, like TableauLooker etc., so you can see data the way you want.

3. Act

Now the trickiest of all of the “3As” — you need to get managers in stores to do something with business insight.

 
How do you drive action?

The nice thing here is that today you have a powerful tool to do that — the cell phone.

We think all insights need to be:

  • Actionable: something the person can do e.g., change this shift, order this item, talk to this employee
  • Available: delivered to the person in a way they can digest e.g., email, mobile app, push notification etc.
  • Targeted: tailored to the right person e.g., sentiment to the CMO, menu insights to a COO and a forecast to the store manager

Our findings here are that you can so-far on your own (e.g., static dashboards and daily reports), but to get this seamless and tailored it’s much better to go to someone with platform expertise. What that means is you need a web app, and iOS app and an Android app.

Of course, at Tenzo we can do all of the “3As” or even just some of them if you’d prefer. Reach out to us to understand more.

Thanks for reading — reach out if you’d like to talk through in more detail.

How does weather affect restaurant sales?

This is the first of what is intended to be a 3 part series on how to get quality forecasts. We’d love your feedback!

At Tenzo we’ve spent a lot of time thinking about how to forecast accurately and wanted to share a couple of the key insights. Typically we have found:

  1. A smart forecasting algorithm can out-perform a store manager in the long run by 25–50%, but it might miss short term events (e.g., roadworks, staff shortage) that only a manager may know about
  2. Weather and events are a critical element in improving a typical forecast
  3. Rain affects sales, but after a certain amount of rain the impact diminishes. Extreme temperatures (vs. normal for the season) are what cause significant deviations in sales.

How do we think about the impact of machine learning?

The below chart compares a 4-week rolling average (e.g., the last 4 Mondays) to a machine learning generated forecast. We typically find a 4-week average this is the best a good manager can do given their memory for events.

MAPE, for a 4-week average forecast vs. a machine learning generated forecast

 

As you can see — the computer wins overall. There may be days when a manager knows something the computer does not, but overall results tend to this.

Now, let’s look at a chart showing how rain impacts sales for a given location.:

Daily sales variance per mm of rain

 

The result is clear — when it start to rain, sales drop-off, but beyond a certain point — people are no longer driven by the rain.

Now, let’s look at temperature:

Daily sales variance per degree of temperature (celsius)

 

Interestingly — this chart is looking at a day in July. A big portion of temperature will be captured in the normal seasonality (which any computer based forecasting system should capture). However, what becomes apparent is how it’s all about extremes — if the day is unseasonably warm or cold it will dramatically affect sales up to a point.

Note: importantly all of these results will be dependent on the specific location, brand and type of business. That’s why you need a machine!

Thanks for reading, we hope we’ve shown:

  1. How weather can be an important factor for your business
  2. The kind of dramatic improvement you can get by looking at it
  3. How a computer can outperform a typical location manager

Let us know your thoughts!

To arrange a demo of Tenzo, please visit https://www.gotenzo.com/demo.

Case Study: Why Tenzo is a good fit for Macellaio

About Macellaio

Roberto Costa founded the first Macellaio in Italy before coming to London to share what he had learnt over twenty years in the food industry. His concept is always the same, the best way of doing hospitality is without compromising the quality — ever.

Why “Macellaio”? According to Roberto Costa it is a name that aspires to be a praise to the animal, but above all to the work of the artisan farmers that devote their lives to this passionate world. Macellaio RC is a hymn to Italian excellence.

All the products offered in Macellaio are the result, the “fruit” as they like to say in Italy, of dedicated work by artisans and farmers who share the “Italian passion” and the same meaning of “made in Italy”.

The commitment is to offer their clients the excellence of Italian products with no compromise.

 

“Is the only place in london where you can find real Italian meat like fiorentina or tagliata. Strongly recommended!” — Emaserafini on TripAdvisor

“One of our favorite places in London. Great meat and a very nice wine list. Staff is very kind and knowledgeable… Always looking forward to go back.” — KB-Dora on TripAdvisor

Why they use Tenzo

Roberto Costa was looking for a way for the managers of his three locations to have everything under control. With Tenzo, directly on their phone they can check their sales in detail (by location, product category, product item…), all their social reviews (Yelp, TripAdvisor, Facebook, Twitter…), their staff performance and also the forecast of sales for the next week.

In concrete terms, with Tenzo, Roberto Costa and his managers can see everything in one place, simply presented and on mobile.

“Tenzo it’s simple and that simplicity helps manage the restaurant in the best way… It’s the best app that I saw, ever” — Roberto Costa, owner of Macellaio RC

Watch the video testimonial

Restaurant Tech Market Map —Integrated vs. Best In Class

We’d like to share today how we see the restaurant tech market map evolve over the next few years: that we are moving from an integrated world where systems would span multiple verticals to one where a collection of specialised systems in each vertical work together.

Integrated World

In the integrated world of restaurant tech, a small number of systems managed the restaurant. There would typically be a point-of-sale (POS), such as NCRPositouch or Zonal where the data would sit on a computer in a back room, a back of house system such as Fourth Hospitality and an accounting system such as Sage. These systems would sometimes talk to each other. The tech lacked in depth functionality as they were stretched over many verticals. It would be difficult to get insights out as the data was fragmented and not readily available.

The Best In Class World

The best in class world that has now emerged is one in which many systems built by different entities communicate with each other to deliver more value to the restaurant. It also means that restaurants have more choice in each vertical and therefore have the opportunity to choose the best in class.

When choosing a technology in the best in class world, you should make sure that the data they collect is available to other systems via an API.

We’ve explored the main verticals and some of the options available:

Tablet POS platforms — These companies offer tablet-based point-of-sale systems for restaurants, aiming to give team members faster and more mobile ways to process transactions. There are a number of options here. Revel and Lightspeed have both raised in excess of $100m. Most have robust systems with reliable APIs which can connect to your accounting software, loyalty systems, payment systems.

 

Staff Scheduling — When I Work (have raised $24m) and Nimble Schedulehave a large installed base and offer APIs that will allow you to pull relevant data out of their system.

On-demand labour — there are several companies that are helping restaurants plug short term gaps in their staff by offering on-demand team members. Notable ones include Catapult and TotalJobs.

 

Internet-of-Things (IoT) — these include footfall sensors (like Hoxton Analytics), smart kitchen sensors (such as Casabot), guest wifi (like purple wifi), digital displays (Enplug) or phone charging stations (powermat).

 

Customer loyalty — The main players in the restaurant loyalty space include FiveStars ($90M in funding), LevelUp ($53M in funding), and Belly ($26M in funding). These companies reward systems, offer points and sometimes pay-by-phone options for customers, as well as limited analytics and marketing options for restaurants.

Purchasing and inventory — Companies like BlueCart ($4M in funding) or SimpleOrder help restaurants track inventory, improve supplier communications, aggregate supplier orders, and analyse costs.

 

Reservation platforms — there are several platforms here but one that is emerging from the crowd is Velocity.

 

Restaurant music — These startups provide smart music systems for restaurants and cafes. Ambie.fm matches the right music the store. TouchTunes ($65M in funding) offers a “digital jukebox” with a companion mobile app for guests, while Rockbot ($6M in funding) gives clients like McDonaldsPanera, and Buffalo Wild Wings a digital music dashboard with curated music stations.

 

Actionable Insights — Tenzo can bring all the data that these systems collect, apply machine learning and data science to them in order to deliver short actionable insights to the right person, at the right time on the right device.