DoorDash and Machine Learning

How DoorDash uses machine learning to power its logistics platform

Doordash and the Food Delivery Industry

DoorDash is a triple-sided marketplace and logistics platform that enables consumers to order food on-demand from restaurant merchants that are then delivered by a fleet of delivery people, called “Dashers”. Consumers are Doordash’s B2C customers, merchants are Doordash’s B2B customers, and Dashers are contractors employed by Doordash who deliver meals from merchants to consumers in their own time.

The food delivery space is highly competitive[1]. Many large players, such as GrubHub, UberEats, Yelp’s Eat24 and DoorDash, vie for dominance, while the threat of new entrants from companies like Google and Amazon looms large. To stay competitive in the food delivery space, DoorDash needs to be better than its competitors at delivering against what the merchants and consumers care about. This includes selecting and surfacing the right restaurants to consumers, minimizing delivery times and making sure that the supply of Dashers meets the consumer demand for food deliveries at every given point in time. Machine learning is a critical tool that enables DoorDash to deliver against all of these key objectives.

Present Uses of Machine Learning

DoorDash uses machine learning to present a personalized selection of recommended restaurants for users based on their past search and order history. Like traditional recommender systems (e.g. Amazon’s product recommendations), DoorDash has to handle cases where new stores or consumers enter the system and manage the tradeoff between relevance versus diversity. Unlike traditional recommender systems, DoorDash’s personalization mechanism faces the issue of sparsity: not every consumer can see every store[2]. By showing users restaurants they are likelier to order from, DoorDash has lifted its conversion rate from search to checkout by 25%[3].

Unsurprisingly, consumers care about both getting their food quickly and getting a reliable estimate of their delivery time. Predicting the delivery time enables DoorDash to assign their Dashers optimal routes and orders, which drives efficiency as measured by delivery time per order and Dasher utilization (the number of deliveries a Dasher performs per unit of time). Variability complicates the problem: DoorDash needs to take into account real-world conditions such as traffic and weather; Dasher supply and delivery demand are both constantly in flux; restaurants also vary in the time it takes them to prepare an order depending on how busy they are. The supply of Dashers available to make deliveries at a given point in time also affects delivery times. To ensure that the supply of Dashers meets consumers’ demand for deliveries at any given point in time, DoorDash uses machine learning to forecast delivery demand.

In the medium term, DoorDash is investing in autonomous robots to deliver food to customers. These robots are eventually meant to complement, rather than replace, the activity of human Dashers. While robots perform actions primarily based on reinforcement learning algorithms (separate from classic machine learning), machine learning is still a critical component of robots. Similar to autonomous vehicles, these robots run on LIDAR technology. LIDAR takes raw input from the robot’s camera and sensors and uses machine learning to recognize and classify objects in the robot’s surroundings. Having a fleet of autonomous delivery vehicles at hand serves as a great backup for when the supply of Dashers fails to meet consumer demand, which reduces the variability caused by inconsistent Dasher supply and dramatically cuts delivery times[4].

Untapped Opportunities

One short-term application of machine learning that DoorDash should do is empowering their local merchants with insights from machine learning to fuel operational efficiency. DoorDash can, for example, use machine learning to help merchants forecast demand, price more optimally, increase labor utilization, reduce food waste by optimizing inventory levels and select the right menu items to offer diners.

DoorDash can also use machine learning to prioritize the restaurants they choose to partner with. Consumers want to find their favorite restaurants on DoorDash. With machine learning, DoorDash can predict the types of restaurants attributes that will be popular with users and rank these restaurants accordingly.

In the medium term, DoorDash should continue developing their delivery robots to make them ready for mass adoption: the robots need to be able to reliably navigate themselves to the proper destinations, interface with local merchants (who are often not very tech-savvy) and recognize the correct orders. Moreover, DoorDash’s ability to grow its user base is currently limited by its Dasher capacity: if DoorDash grows too quickly, it runs the risk of failing to fulfill every order. Autonomous robots solve this problem and allow DoorDash to aggressively grow its user base.

Open Questions

One of the biggest open questions for DoorDash is an ethical one: the rise of delivery robots could eliminate the need for human Dashers, which runs counter to DoorDash’s mission of economically empowering the masses. DoorDash, then, will need to think about how exactly these robots should complement, rather than replace the work that Dashers do

References

[1] DoorDash. “Powering Search & Recommendations at DoorDash – DoorDash.” DoorDash, DoorDash, 6 July 2017, blog.doordash.com/powering-search-recommendations-at-doordash-8310c5cfd88c.

[2] DoorDash. “Welcoming Our Newest Robots to the DoorDash Fleet with Marble.” DoorDash, DoorDash, 16 Aug. 2017, blog.doordash.com/welcoming-our-newest-robots-to-the-doordash-fleet-with-marble-e752a85d6602.

[3] Hirschberg, Carsten, et al. “The Changing Market for Food Delivery.” McKinsey & Company, www.mckinsey.com/industries/high-tech/our-insights/the-changing-market-for-food-delivery.

[4] Marshall, Matt. “DoorDash Sees 25% Lift from AI Recommendations.” VentureBeat, VentureBeat, 18 May 2017, venturebeat.com/2017/05/17/doordash-sees-25-lift-from-ai-recommendations/.

 

(790 words)

 

Previous:

Print-a-Part: How 3D Printing is transforming Medical Device Manufacturing

Next:

Will Zalando stay ahead of Amazon in European online fashion?

5 thoughts on “DoorDash and Machine Learning

  1. The relentless march toward automation and machine learning may be finally coming to the food service industry. I will be interested to see how competition between various delivery service will drive the development of final-mile delivery robots. Given that the delivery service industry provides low-skilled employment for many workers, it is the worrying that the last bastion of human labour, the service industry, may one day be run by hordes of Amazon drones and Dasher robots…

  2. The rise of automation is creating a broad conversation across a variety of industries, from consumer tech to restaurants. On the one side, automation replaces monotonous labor and increases efficiencies. On the other hand, it highlights the need for a more educated workforce, equipping everyone with a skillset for the future. In the case of DoorDash, I believe they are currently using machine learning in a way that is synonymous with most well-funded start-ups, using recommendation and delivery algorithms to make everything easier for the customer. However, I really believe robotic delivery is in the relatively distant future for the majority of Americans. There are numerous logistical implications, from safety precautions to competition with that one big e-commerce company, that accompany thousands of robots moving amongst crowds of people simply to deliver a single California Roll.

  3. Great topic choice! 🙂

    While I obviously have quite a few opinions here, I’ll constrain my comment to two things:

    1.) I love the short-term suggestions given here. DoorDash has carved out a niche in an otherwise crowded competitive space by focusing relentlessly on the merchant. Without these largely SMB partnerships, the marketplace holds no inherent value for the consumer. I’d suggest that the majority of capital recently invested in the company should be used to expand to new areas and sign the best restaurants in the world. When going into new markets, it is absolutely imperative that DoorDash prioritizes its sales efforts to the best possible restaurant partners. This effort requires significant predictive analytics and could make use of machine learning models to leverage third party data such as Yelp, Foursquare, population data, etc. with the goal of selling the best merchants in a new, unknown area. Using merchant intelligence tools would also allow DoorDash to sign these merchants at higher commissions and at a faster pace. In the end, using ML to help the merchants inherently trickles down into helping the DoorDash marketplace and could actually lead to another revenue stream for the company.

    2.) I’m much less bullish on robots as a long-term strategy. The gig economy is going to continue to grow with the rise of more automation in the workplace, giving DoorDash and other IC-focused companies a large pool of on-demand workers. Uber is able to supply their significant rider demand with drivers and I believe companies like DoorDash will be able to scale their driver base alongside. In fact, many gig economy workers multi-platform so each incremental worker can add capacity to each company at some level. Food delivery is such a time and labor intensive process, robots just don’t increase efficiency enough to be worth it. At peak dinner rush, the Cheesecake Factory would have 50 robots waiting in line. If anything goes wrong, the order is hopeless as the robot doesn’t have the emotional of intellectual ability to triage the issue. Robots are phenomenal for drumming up press though!

  4. Although I feel technology has a critical role at companies like DoorDash, I don’t know how concerned I am with autonomous robots taking over the gig industry. Food delivery entails a considerable degree of customer service and I feel customer service is one of those functions in which computers will not become completely ubiquitous, and is instead a good example of a machine+man/woman use case. Customer service requires empathy and an understanding of the customers emotions, which often drives decision making. One of the largest limitations of AI is its inability to compute emotion, thus I don’t see computers taking over.

  5. This is a problem with many companies in the tech space. Robots will replace the jobs of dashers in the future, it’s only a matter of time. Is it really DoorDash’s place to solve this issue? DoorDash could provide resources to their employees to allow them to be successful once they move on from the company, but I don’t think they should feel responsible for doing so. If they want to help these employees stay with the company, it is possible that they create new lines of business that can employee these Dashers in other capacities.

Leave a comment