Recipe Generation at Jumbo Supermarkten

18

October

2024

No ratings yet.

Leveraging Generative AI tools to increase customer value

In recent years, AI tools have become increasingly integrated into our daily lives. One area where AI can make a significant impact is in the realm of grocery shopping. Jumbo, one of the leading supermarket chains in the Netherlands, already has an app that allows customers to earn points and view weekly discounts (Jumbo Extras). But we believe we can improve it further with Generative AI models.

In today’s generation, one of the challenges many people face is meal planning, often leading to leftovers going to waste. Our solution involves using AI to address this issue. While Jumbo’s app already provides product search and shopping assistance, it lacks a personalized, dynamic element. Our proposed AI feature will add value by generating recipes tailored to the customer’s preferences. Users can input the ingredients they have at home, and the app will generate a recipe while also suggesting the remaining ingredients that need to be purchased. This not only reduces food waste but also provides a practical way to utilize leftovers in new recipes.

Furthermore, if the app recognizes a user’s preference for, say, Italian cuisine, it will recommend a pasta recipe and offer a discount for purchasing the recommended ingredients. This is made possible by the AI analyzing consumer behavior, leading to increasingly accurate recommendations with each visit. This personalized approach encourages customers to try new recipes and products, thereby enhancing their shopping experience and boosting supermarket sales.

Essentially, this feature acts as a personal shopping assistant, catering to the user’s tastes and preferences. Over time, it can enhance customer satisfaction, loyalty, and retention by making customers feel valued and understood. From the company’s perspective, this strategy can lead to increased sales, as recipe-based discounts incentivise customers to purchase more products and explore niche items. Additionally, this initiative will help reduce food waste by providing insights into which products need to be consistently stocked and which items can be reduced in quantity.

Based on the proposed solution detailed in the assignment, we have built and deployed a working prototype, that mocks the Jumbo mobile app and adds the Recipe Generation tools. The image on the left represents the Homepage mockup. The two images below on the left are screenshots of a user interacting with the Generative AI model that generates recipes from existing ingredients, while adding missing ingredients as a separate list, which can be added to the Shopping Cart. The final picture represents the actual products suggested by the AI, added to the shopping cart.

Would you use AI tools to enhance your grocery shopping experience? Let us know below.


Group 10
Team Members:

  • Alexandra Stancu (697789ms)
  • Codrin Socol (744294cs)
  • David Peța (744425dp)
  • Ioana Buia (741838ib)

Reference List

Please rate this

AI-enhanced coding: The future of software development is here

26

September

2024

5/5 (2)

Writing source code is not always an easy task. Sometimes, a bug occurs that it is so hard to find, you spend hours and hours searching through the Internet on websites like Stack Overflow [1] to try and find someone that had that issue before and how they fixed it. Some other times you have to rewrite the same code over and over again, which can be boring.

GitHub Copilot [2] is a Generative AI tool that helps developers with writing code, increases productivity and decreases development times, while also automating the “boring” parts of writing code. The tool offers two main features:

  • Code completions: The tool auto-generates code on-the-go while you are typing, which you can add at any step. You can also write comments and the tool will treat it as a prompt to generate code.

Using a comment to instruct GitHub Copilot what to generate, using code completions.
The red-colored code is the AI suggestion. If suggestion is accepted, it is turned into normal-colored code.

  • Chat Discussion: The tool also offers a way to interact with the model via chat, similar to the ChatGPT-like tools.

Using GitHub Copilot Chat to debug code and fix errors. It can also be used to generate documentation, tests, explain selected code or optimize algorithms.

I have been working as a Software Developer for the past 2 years. Ever since I started, I have been using GitHub Copilot to help me automate (part of) the software development process, especially with writing tests, documentation and to debug errors. Tasks that used to take up to a day to complete were resolved in a matter of one or two hours. Compared to the projects I was involved before such tools emerged, I can definitely say they were a game-changer. Tasks were being completed faster, the code written had better quality and I had time to focus on more important tasks, like improving the customer UI experience.

From my experience, Copilot is very good at suggesting repeating (or similar) code from within the project, as well as general code structures identifiable from other projects. It also has very good understanding of error codes in most programming languages I have used, so it is very powerful to use for fixing errors. This type of debugging usually took a long time, browsing through Stack Overflow posts and trying different suggestions until finding what could be a possible solution. The GitHub Copilot Chat was able to provide a working solution within minutes in most of the cases and with good explanations too of what was going wrong.

Even though it sounds like this is the perfect tool for coding, there are some limitations I found. Sometimes, I noticed it is slow in providing an answer. Theoretically, you can switch between different suggestions, but so far I noticed that feature is broken, as I always get “no alternative suggestions”. Moreover, many times, when you are writing a new feature from scratch, it is not good at giving initial suggestions. I expect this is a “cold start” effect, so until you give it some more input, it will not give suitable suggestions.

The biggest issue I have encountered so far is related to privacy. GitHub (Microsoft) collects data from your (private) repositories with code when you use this tool. Thus, some companies may be reluctant to let their developers use such tools, as sensitive data can leak. There is history on this topic, as Microsoft has been accused of copyright infringement multiple times when developing Copilot, as they used copyright-protected code to train their models [3].

All in all, I am really happy with how this tool incorporates with my work and I use it daily. Up until now I have had free access to this tool (as a student), but even if I would have to, I would 100% pay to use this plugin. I am confident that in the future, the quality of this service will increase continuously and I am looking forward to seeing what other alternatives emerge on this market! Having an AI pair programmer really makes a difference!

Have you used any similar Gen AI tools with your work? How did you find it? Let me know below!


References:

Thumbnail photo: Generated with DALL-E, made by OpenAI. Prompt: Generate an image about a programmer that uses a Generative AI tool such as Microsoft GitHub Copilot as a pair programming tool to enhance their software development cycle.

  1. Stack Overflow – where developers learn, share, & build careers. (n.d.). Stack Overflow. https://stackoverflow.com/
  2. GitHub Copilot · Your AI pair programmer. (2024). GitHub. https://github.com/features/copilot
  3. Vincent, J. (2022, November 8). The lawsuit against Microsoft, GitHub and OpenAI that could change the rules of AI copyright. The Verge. https://www.theverge.com/2022/11/8/23446821/microsoft-openai-github-copilot-class-action-lawsuit-ai-copyright-violation-training-data

Please rate this

Virtual Vacations: Is digital sightseeing the new disruptor of the tourism industry?

13

September

2024

No ratings yet.

Ever dreamed of exploring your dream destinations from the comfort of your couch? To instantly jump from the Pyramids of Giza to the Colosseum in Rome or the busy streets of The Great Bazaar in Istanbul?

It may sound like fiction, but the technology is here. Virtual Reality (VR) headsets offer the user a fully immersive experience in a digital world or environment. But could you be able to use a VR headset for a vacation?

I have used a VR headset a few times to play some PC games, but I never owned one. During one of the course’s lectures, where we discussed emerging technologies, like AR/VR or NFTs, I wondered if I could use this technology to see the world without stepping outside of my (student) room. Well, it turns out you already can.

After a little digging on this topic, I found out that Google has launched Google Earth VR as a game on Steam [2], and I was astounded! Only with this app, you can travel to any place in the world and see it from satellite or via Google’s Street View! What is even cooler, is that many of the famous landmarks have been laser-scanned and are available on this app with high resolution 3D detailing.

Neuschwanstein Castle in Germany, as seen on Google Earth VR [3]

Google also invested in their “Arts & Culture” project, which partners with 2000 museums to offer digital (and also VR) tours. Here is a 360-degrees/VR video about the The Fall of the Rebel Angels (1562) painting, from the Royal museum of Fine Arts in Belgium, done in collaboration with Google:

What is even better is that Google offers these services for free. So, you can have endless experiences without even paying anything for them.

One of the biggest players on this market is Meta, which even developed their own VR Headset. They are also known for heavily investing into the “MetaVerse”, their vision of Web 3.0.

I have stumbled upon an article on Meta’s blog about “Virtual Vacations” [4]. Their most popular app called “Wander” costs 10 euros and allows the user to travel anywhere in the world or explore how a place used to look like in the past. What is even better, is that you can explore the world in multiplayer, along with your friends. I left videos below of the other 2 apps they were presenting in this blog, they are worth checking out!

Even though this all sounds great, these solutions are not perfect. Many times, the image quality is not the best (assumingly due to performance/storage constraints of the VR headset), which is a factor which reduces the immersion into the digital world. Another factor is the fact that no sound is played that matches the landmark you are seeing, which also weakens the experience. Moreover, a VR headset, if you do not yet own one, does not come cheap. Meta’s most recent one, called Quest 3, starts at 550 euros, while their most expensive one, the Quest Pro is 1200 euros [5].

But I feel optimistic for the future. I see these technologies emerging into strong digital disruptors for the travel industry, in a future where a VR headset is a must in every household, like a TV or a couch. I also think prices will increase for these experiences too. From free / one-time payment, to pay-per-experience or even subscription models, as more users adapt to this new, emerging technology that is Virtual Reality.

All in all, after researching this topic, as a travel enthusiast, I think I may have to buy myself a VR headset soon and start exploring the world digitally :). I would definitely use this to plan my future vacations!

What do you think of digitally traveling in VR? Do you think it has the potential of competing with traditional tourism in the not-so-distant future? Let me know below!


References:

  1. Thumbnail Photo: generated with a community-made GPT that uses DALL-E https://chatgpt.com/g/g-pmuQfob8d-image-generator). Prompt: generate an image about a person using VR headset for traveling digitally.
  2. Google’s Earth VR game page: https://store.steampowered.com/app/348250/Google_Earth_VR/
  3. https://www.vrnerds.de/google-earth-vr-fuer-oculus-rift-erschienen/
  4. https://www.meta.com/blog/quest/virtual-vacation-11-vr-apps-and-films-that-let-you-travel-the-world-from-home/
  5. https://www.meta.com/nl/en/quest/compare/

Please rate this