ML Models Built on Google Cloud Solutions Help You Virtually Participate in National Muffin Day!
2948
Of your peers have already read this article.
2:00 Minutes
The most insightful time you'll spend today!
If you’re here you’re probably wondering: what on Earth is the connection between muffins and machine learning, and what is National Muffin Day? To understand this, let’s start with National Muffin Day: an annual holiday co-founded by Jacob and his friend Julia Levy in 2015 to bake muffins and raise money for homelessness. National Muffin Day will occur on Sunday, February 20 this year. For more information on how to participate in National Muffin Day (which involves delicious baked goods and donations to people in need), please see the information at the bottom of this post. Last year, a colleague connected Jacob with Sara, who had done several baking projects that used machine learning to generate new recipes. They decided to collaborate for this year’s National Muffin Day, adding a new muffin recipe created with the help of machine learning.
In this post, we’ll explain how Sara used Google Cloud to develop a new muffin recipe, show you how you can participate virtually in National Muffin Day, and of course—share the recipe.
Machine learning for muffins
At its core, machine learning is the process of finding patterns in data and using those patterns to make predictions on new data. After a lot of baking over the past few years, Sara learned that baking is also based on patterns. For example, the ratio of flour, fat, liquid, and sugar that make up a cookie is very different from the ratio of those ingredients for a bread, a pie crust, or a muffin. She used that discovery to create a recipe for a hybrid cake + cookie, and a cake filled with Maltesers. Next up: muffins!
The first step was figuring out how to translate the task of generating a new muffin recipe into a machine learning task. To solve this, she planned to use numerical data on the amounts of different ingredients in a muffin recipe to train the model. Sara considered two types of models for this task: classification and regression. A classification model would categorize muffin recipes into different muffin types based on their ingredient amounts, and a regression model would do the reverse: take a type of muffin and return the amount of each ingredient needed to make it. She decided to build a regression model, since it would be more fun for the model to return ingredient amounts, rather than tell you which type of muffin recipe you’re already making.
Implementing this first required identifying a few muffin categories and collecting recipe data. This presented a new challenge, since her previous baking models used categories for distinct baked goods (i.e. cakes, cookies, breads). After scouring through quite a few recipes, Sara discovered that many muffins fall into two types: those that use only traditional ingredients as their base (flour, sugar, butter, milk, etc.), and those that include an alternative ingredient, most commonly a pureed fruit, to make the base (like bananas, applesauce, or pumpkin). Using those two categories, the model would take the type of muffin as input and return the amounts of base ingredients required to make that recipe. Here, the inputs can be any values adding up to 100%:
The next step in the ML process was collecting recipe data to use for model training and narrowing down the ingredients used to train the model. Sara wanted the model to learn the combination of core ingredients that make up a muffin batter, rather than flavorings and additions like blueberries, vanilla extract, or chocolate chips. These tasty additions could be added after the model helped create the muffin batter. Once she gathered enough recipes, she removed extra ingredients for training purposes and converted ingredients from different recipes into the same unit (grams, milliliters, and teaspoons).
Building a muffin model with Vertex AI
Sara uploaded the muffin ingredient data into BigQuery, and then created a notebook instance in Vertex AI Workbench to analyze the data. With the new Workbench managed instances, you can interactively query BigQuery tables directly from your instance and copy the code to download your data to a notebook as a Pandas DataFrame:
From her notebook instance, Sara experimented with different ML frameworks and model types. She landed on a Scikit-learn regression model to solve this task, and to mimic a real-world production environment, decided to convert this workflow into a ML pipeline. Using the Kubeflow Pipelines SDK, she ran the following on Vertex Pipelines:
The first component reads the ingredient data from BigQuery and converts it into a Pandas DataFrame which is passed to the next pipeline step. In this step, we train a custom Scikit-learn model on the recipe data. Finally, this model is deployed to an endpoint in Vertex AI. To put it all together, Sara built a web app that allowed her to easily generate ingredient amounts for different muffin types. The web app uses the Vertex AI SDK to call the deployed model endpoint and return ingredient amounts.
The recipe
With a deployed recipe generation model, the only thing left to do was test recipes in the kitchen! Because the model only returns ingredient amounts, there were still many key human elements to complete the baking process: adding yummy additions to the core muffin batter, making adjustments to optimize taste, determining the method for adding ingredients, baking time, and more. After testing a few recipes generated by the model, we landed on a favorite which we’re very excited to share with you here.
Berry ML Muffins
Makes 12 muffins
Flour 285 grams (2 cups)
Granulated sugar 250 grams (1 cup)
Baking powder 2 teaspoons
Baking soda ¼ teaspoon
Salt ½ teaspoon
Cinnamon ½ teaspoon
Milk 170 ml (⅔ cup), room temperature
Butter 55 grams (¼ cup), melted and slightly cooled
Eggs 1 egg plus 1 egg white, room temperature
Canola or vegetable oil 50 grams (¼ cup)
Sour cream 50 grams (3 tablespoons + ¾ teaspoon), room temperature
Vanilla extract 1 ½ teaspoons
Blueberries or raspberries 240 grams (1 ½ cups)
Coarse sugar, like demerara or turbinado (optional for topping) 1 tablespoon
- Measure your three cold ingredients and allow them to come to room temperature: 1 egg + 1 egg white, sour cream, and milk.
- Preheat the oven to 375 F / 190 C. Line a 12-muffin tin with cupcake liners or lightly grease with baking spray.
- In a large bowl, whisk together flour, baking powder, baking soda, salt, and cinnamon. Set aside.
- Melt your butter in a medium heat proof bowl, and allow it to cool slightly for a few minutes. Whisk in sugar until combined. Then add egg, oil, and vanilla, milk, and sour cream and whisk until fully incorporated.
- Pour the wet ingredients into the dry ingredients, mixing with a spatula until just combined. Be careful not to overmix, it’s ok if there are a few lumps in your batter.
- Prepare your fruit. If you can’t decide whether to use blueberries or raspberries, divide your batter into two bowls and do both! Crush half of your fruit and fold it into the batter. Then mix in the remaining whole berries.
- Divide the mixture evenly into the muffin tin. Optionally (but extra tasty), sprinkle the tops of each muffin with about ⅛ teaspoon of coarse sugar. Turbinado or demerara sugar work well for this. This will caramelize and add a nice texture to the tops of your muffins.
- Bake at 375 for 22 – 24 minutes, or until a toothpick inserted in the center comes out clean. For best results, do a toothpick test in a few muffins since not all ovens have an even temperature throughout. Let the muffins cool in the muffin tin for a few minutes, then transfer to a wire rack to cool completely.
- Enjoy!
How can you participate in National Muffin Day?
Participation in National Muffin Day is as easy as 1-2-3!
- On February 20, Bake Muffins. It’s time to dust those muffin tins, grab your blueberries, chocolate chips, rhubarb, and favorite ingredients, and create some magical scrumdiddlyumptiousness! If you want to join Jacob in a virtual baking party, you can register here.
- Then, Give. In non-pandemic years, we asked our bakers to personally hand muffins to hungry folks in their cities. While this is a valuable and rewarding experience, the current state of Covid means this practice is still unsafe, so we request that you refrain from doing this. Instead, if it feels safe, we encourage you to take your delicious baked goods and donate them to local homeless shelters, which can distribute them to those in need. Alternatively, you can share your muffins with friends and families and then make a donation to an organization that benefits people experiencing homelessness, like the ones listed below in step 3.
- Share Your Muffin Pics on Social Media. We’d love to see your muffins! Share your pictures on Twitter or Instagram with the hashtags #givemuffins, or share them to our official Facebook Event page. For each individual baker who participates, we will make donations to Project Homeless Connect, which provides much needed resources to people experiencing homelessness in San Francisco, Family promise, which supports unhoused families nationwide, and Pine Street Inn which provides resources for people experiencing homelessness in Boston. Donations will be on a per-baker basis (with up to $80 donated per baker!), so please feel free to loop in your significant others, kids, nieces and nephews, roommates, friends, and anybody else with a giving spirit who loves deliciousness!
AI Solutions for Government Organizations: How to Get Started
4378
Of your peers have already read this article.
3:00 Minutes
The most insightful time you'll spend today!
Cloud-native features are helping public sector teams innovate faster than ever. Ideas discussed in a morning meeting can be a working proof of concept later that day. Managed services can remove administrative burden and reduce the steps needed to design and provision cloud infrastructure. Security can be built-in from the beginning with Identity and Access Management (IAM), Virtual Private Cloud Service Controls (VPC-SC), and Data Loss Prevention (DLP). Short-lived services and infrastructure-as-code allow rapid and cost-effective prototyping. These technologies can be used to architect a solution that follows the principle of least privilege and helps you secure your data.
So the question becomes: given the complex problems agencies face, where do you start? Google Public Sector now offers “Getting Started” and “Scaling” service offerings for CCAI, DocAI, and BigQuery to help you jumpstart your AI journey, based on where you are.
Complex problems, simpler AI-based solutions
Solving more challenging problems with cloud-native technology doesn’t have to be overwhelming. You can approach them the same way you might solve a puzzle: start with one piece that follows another until the larger picture takes shape. Though you can simplify the steps, solving these problems still requires powerful tools. Google Cloud’s AI/ML capabilities may be the answer for your team.
Google Public Sector is making it easier to get started with advanced technologies, beginning with artificial intelligence and machine learning (AI/ML) workloads for government organizations, and it’s something you can do now, one piece at a time.
Automating your FAQs with CCAI
Does your agency require a team to answer commonly asked questions? What if you could train an agent to answer questions immediately and operate 24/7? Contact Center AI (CCAI) can do this and more. Already using CCAI and need the agent to level up to address complex interactive dialogs? Getting Started with CCAI and Scaling with CCAI are new Google service offerings specifically designed to help public sector organizations tackle situations like these.
Automate data entry with DocAI
How many hours does your team spend manually reviewing or entering data from standardized forms? What if you could automatically pull data right from the page? Google Document AI (DocAI) specializes in exactly this—even if the form has handwritten text. Getting Started with DocAI and Scaling with DocAI are new service offerings that help you remove this burden from your team. DocAI automates data entry and makes that data available to other teams while prioritizing both security and ease of use.
Making data and insights accessible with BigQuery
Then there’s all your existing data. You may have years of it stored in many places, and you may not have a way to make use of it when you need it. BigQuery is Google’s enterprise data warehouse. It was designed for data analytics—looking back at historical data to make conclusions about it. But BigQuery’s analytics don’t stop there. It can also look forward in time to make predictions, often using the same datasets. Getting Started with BigQuery and Scaling with BigQuery are new service offerings that help you take your first steps toward AI/ML capabilities by starting with a single table or pipeline that can help make sense of all your data.
The best help is the kind that meets you where you are and gets you where you want to be. Google Public Sector’s new service offerings do just that: help you work through complex problems by meeting you wherever your starting line is, whether you’re ready to start or ready to scale. Let us know if you would like us to contact you about the services mentioned in this article. Let’s solve your highest impact problems together, one puzzle piece at a time.
How Recommendation AI Helps Retailers Optimize Click-through and Conversion Rates
7052
Of your peers have already read this article.
3:00 Minutes
The most insightful time you'll spend today!
Time to go outside again, I guess. I’ll need a sun hat. Sunscreen. Maybe some new sandals? What else?
With the Recommendations AI service, I might be reminded to grab a reusable water bottle and a swimsuit. Or some after-sun aloe lotion. Good thing, cause I’ll need it.
Recommendations AI is a solution that uses machine learning to bring product recommendations to their shoppers across any catalog or client list. This service is part of our full suite of Retail solutions. When you integrate with the Retail API, you get the benefit of Google’s Product Discovery. Integrating once to reap the benefits over and over. Recommendations is the starting point, and you can easily extend into Retail Search and Vision Product Search in the upcoming future.
The Recommendations solution is fully managed, global-scale and powered by deep learning, so you can focus on a great shopping experience and let someone else worry about the infrastructure.
Compared to baseline recommendation systems used by customers, Recommendations AI showed double digit uplift in conversion and clickthrough rates in A/B experiments controlled by the customers. You can optimize for click-through, conversion or session revenue, and fine tune the models to make sure you omit out-of-stock items or duplicates, for example.
So how does it work, and how do you get started? Read on, and we’ll walk you through the pipeline, starting with the data you already have to placement in your online store.
Formula: Data -> Model -> Placement
You start with your catalog, the list of all the things (postcards, movies, pie recipes) that you want to show your customers. Then you ingest your PII-redacted user events -this is the historic event data like home page views, add to cart events and more along with real time user events. This user event is joined with the product catalog and items that allows us to construct the sequence of shoppers’ activity, thus being able to predict what the shopper has a high propensity to purchase next. The user events can come from both online activity across devices or offline store purchases
The recommendation model will return a list of products, which are the recommendations. The brains of the operation, if you will. This model is trained using all the data that you ingest, using the latest neural network models and techniques that Google has built expertise over the years in flagship products like Youtube and News, that allows us to uncover shopper intent, so it can best predict the right recommendations to show to the right people.
Every model outputs a list of product identifiers, but where do they go? They go into placements, the spots, panels, carousels on your customer’s journey interacting with your brand that you’ve set aside to highlight recommendations. A model can send recommendations to one or more placements, but each placement only receives information from one recommendation model. Your pages will then need to render the products with the right images, text or other metadata, using the product ID that is returned by the model.
What do recommendations look like?
Let’s start by browsing our postcard-selling website, where I’ve been buying some vintage California postcards already. The recommendations algorithm has caught on to my interest, showing me other potential cards to purchase based on my history:
Put your data to work
To get started we need to bring your data into the recommendation model, so it can understand your customers, your inventory, and your sales patterns.
The model takes in the product catalog you use, and metadata about those products to better understand nuances in assortment, pricing and variables like size and style. You might already have this data stored in BigQuery or Merchant Center, and hence we provide easy integrations that you can leverage to get started even faster.
As for the user events, don’t worry if you already have systems in place to capture web and mobile activity. We make it easy to bring in your real time event logs by providing seamless integrations with Google Tag Manager, Javascript pixel, or even historic events from Cloud Storage, BigQuery or using inline API or JSON, so you can immediately train the models on this imported data. All this allows you to kickstart integrating with Recommendations AI in a matter of days.
The models then construct a sequence of activities that the user went through and joins with the products that the user engaged with. Once your data is ready to go, it takes a few days to train the model. Next onto making the data work for you.
Quickly customize your model
Setting up your own recommendations project in the console gives you the ability to choose what sort of model to train (based on what recommendations you want to generate) and your objective. Are you optimizing for click-through rate–more people click on the recommendation links or products–or for conversion rate–more people choose or buy what was suggested or revenue ?
Different models can be optimized for different optimization goals.; the GCP console explains what each one can do and how you can choose to optimize it.
Let’s unpack some of this terminology real quick.
We’ve got three model types:
- Recommended for you – Means we think these are items you’ll want to buy, based on your history; this is usually used on a home page to showcase items.
- Others you may like – Means if you’re browsing the page of a water bottle, we will recommend alternative brands of water bottles that you may like as well as a backpack, based on your engagement history.
- Frequently bought together – Means that when anyone buys sunscreen, we notice that they often also buy aloe lotion, so we will surface those items when someone adds any one of them to their cart.
And then we have three business objectives that the models optimize for:
- Click-through rate – How frequently did somebody click on a recommended item?
- Conversion rate– How frequently did somebody add a recommended item to their cart?
- Revenue per session – How much money did the recommendations generate for you?
Deliver anywhere along the journey
Now that you’re all set up in the Retail AI console, you can test out the recommendations in the console, even before you deploy to production.
You can integrate Recommendations into your frontend by calling the Predict APIt. The placements of recommendations will report data back into the dashboard and you can analyze and measure success for future iterations.
On top of that you can use the recommendations for other parts of your customer’s journey. Email promotions, storefront kiosks, display ads or follow-up notifications can include recommendations based on past activity and cart contents. The model gives you useful product recommendations for a wide variety of touchpoints and steps in the purchasing process.
More best practices, and guides, are available inside our documentation.
How to get started
Training your own models can be tedious, time-consuming, and expensive. On top of that it requires deeper data science expertise to set up. Let us do it instead!
You can see how IKEA Retail uses Recommendations AI in this recent talk and blog from the Google Cloud Retail Summit..
To get started today you’ll need to make a Cloud project and enable the Retail API, which then allows you to access all the recommendation tools in one menu. Bring in your catalog and purchasing data, define a placement or two, and you can start putting recommendations on your site in a matter of days.
Cart.com to Transform e-Commerce for Brands Globally
8758
Of your peers have already read this article.
1:30 Minutes
The most insightful time you'll spend today!
The ecommerce playing field has been hard to navigate for most retailers, and Cart.com is on a mission to change that. Traditionally, retailers needing to run their online store, order fulfillment, customer service, marketing, and other essential activities have had to cobble together systems to get the capabilities they need – much less having access to analytics across these functions. The result is costly, siloed ecommerce operations that are difficult to manage and scale.
It’s clearly not a formula for success, yet that’s the reality facing most retailers. Cart.com, in contrast, has set out to democratize ecommerce by giving brands of all sizes the full capabilities they need to take on the world’s largest online retailers. Our end-to-end environment empowers retailers to keep more of their revenue, set up proven strategies for managing all aspects of their business, and act on valuable insights from customer data every step of the way.
Together with our talented team, we’re building a unified ecommerce platform that already provides value to many leading or up and coming brands including Whataburger, GUESS, Dr. Scholl’s, Rowing Blazers, and Howler Bros.
We’re excited about the opportunity ahead as we reimagine traditional approaches to online sales, fulfillment, marketing, accessing growth capital, providing a unified view of all ecommerce and marketing analytics, and other activities. Expectations for Cart.com are high, and we are building a company that can scale to $100B in revenue and beyond. Supported by the Startup Program by Google Cloud and Google Cloud solutions, we’re establishing a technology platform to transform all aspects of ecommerce for brands worldwide.
Partner in disruption
At Cart.com, we’re currently targeting an underserved market. Our ideal customer is beyond demonstrating product-market-fit and is now at an inflection point seeking a growth opportunity. Typically, those companies are generating between $1M and $100M in annual revenue. We’ve seen an enthusiastic response from brands and retailers as well as investors, with backing from investors in just over a year totaling $143 million in three funding rounds.
Our strategy is to build an integrated ecommerce model that combines best-of-breed solutions, many of which we gain through acquisitions and then build upon to provide a streamlined and fully integrated experience for our brands. We’ve made seven acquisitions so far to round out our online store, order fulfillment, marketing services, customer service, and we have launched some integral partnerships including easy access to growth capital through our relationship with Clearco and product protection for customers on every purchase with Extend. Instead of acquiring a data company, we’re building our data platform on Google Cloud, across each operating function for a single-view for brands to harness actionable data. We see Google Cloud as the leader for data management, analytics, machine learning (ML) and artificial intelligence (AI).
Other reasons why we’re building our business on Google Cloud include scalability, excellence, security, reach, and data analytics that are far superior to other environments.
We also feel a cultural and mission alignment with Google Cloud and envision leaning into a long-term partnership of marketing, selling, and disrupting the disruptors together. Equally important to us are the investments Google Cloud is willing to make in early-stage companies like ours. The support through the Google Cloud for Startups program has been outstanding.
Built on Google Cloud
A wide range of Google Cloud solutions provide the foundation for our platform. For instance, Cloud Pub/Sub keeps our services communicating with one another. We rely on fully managed relational databases, like Cloud SQL and Cloud Spanner, to securely handle the huge volume of brand and shopper data generated every day.
Cloud Run allowed us to develop inside of containers before our Kubernetes infrastructure was ready to go. Now, we are taking advantage of all the capabilities in Google Kubernetes Engine. BigQuery integrates with all Google Cloud solutions and offers true data streaming natively out of the box, along with Dataflow for advanced analytics. We also use Container Registry to store and manage our Docker container images. Right now, we’re testing Cloud Composer to evaluate using it for data workflow orchestration instead of Apache Airflow.
The openness of the Google Cloud environment is further enabled by Anthos, which we may deploy soon to perform data integrations quickly as we acquire more companies over the next year. For example, if we acquire a company using Azure, we can easily align it with our Google Cloud ecosystem.
Enabling ecommerce 2.0
Recently, our team has been experimenting with Google Cloud Vertex AI and the fully managed services of AI deployment and ML operations. The capabilities would save us substantial time in the management of the ML lifecycle which allows us to focus more on developing proprietary AI that will transform commerce at scale.
Because Google Cloud is so far ahead in data science, our teams benefit from deep Google Cloud expertise as we look to provide brands with unmatched insights into customers to improve services and revenue. We’re also planning to test Recommendations AI among other tools to deploy customer product recommendations and personalization as turnkey productized offerings. Moving forward, we will likely use Bigtable to aid in serving machine learning to hundreds of thousands of brands due to its low latency and scalability.
Fanatical about brand success
We know that our work with Google Cloud for Startups and use of Google Cloud solutions for best-in-class data management, analytics, ML, and AI will enable us to offer even more transformative services to brands.
We also see the opportunity to use our platform and customer insights to break down barriers between brands, enabling retailers to share information and work better together when it’s in their best interests. What we’re building today on Google Cloud is fundamentally changing what’s possible for retailers of any size everywhere.
As a startup, when recruiting talent or working with prospective customers, it helps to share our success with Google Cloud. We view them as an extension of the Cart.com team. It also validates our business as we continue building a more integrated, holistic approach to commerce that opens new opportunities and drives growth for brands worldwide.
For more details about Cart.com’s vision for unified ecommerce, check out our video.
If you want to learn more about how Google Cloud can help your startup, visit our page here to get more information about our program, and sign up for our communications to get a look at our community activities, digital events, special offers, and more.
3308
Of your peers have already watched this video.
44:14 Minutes
The most insightful time you'll spend today!
Supercharge Marketing with Ready-Made, Centralized Smart Analytics
Your company has lots of valuable marketing data, but it’s spread across many systems and teams. That’s a problem. In fact, only 13% of organisations feel like they’re making the most out of their available customer data today.
And the reason is that data–marketing and customer data–is spread across many different places.
With Cloud, you can bring this data together in one place so you can better analyze and activate it.
Find out how new GCP tools for marketers and hear directly from brands, including Rituals and Waitrose, who are using them to solve use cases like audience segmentation, purchase prediction, and measuring lifetime value.
You’ll learn how Google Cloud is helping IT and marketing teams accelerate digital transformation within their organizations, to be data-driven, and customer-centric.
You’ll walk away with an understanding of how to adopt technology that transforms the way your company delivers marketing campaigns and customer experiences.
4889
Of your peers have already downloaded this article
1:30 Minutes
The most insightful time you'll spend today!
Artificial intelligence and machine learning are already transforming the technological landscape. From digital assistants to image-recognition software to self-driving cars, what was once the stuff of science fiction is now becoming a reality. But what exactly does it mean for marketing and advertising executives?
It could get us closer to one of advertising’s most-sought goals: relevance at scale. Before then, we’re going to see changes to the way we do business.
Technological advances have always created new opportunities for storytelling and marketing. Just as the advent of TV brought an era of truly mass advertising and reach, and the internet and mobile brought a new level of targeting and context, AI will change how people interact with information, technology, brands, and services.
A big part of the opportunity for marketers is how AI will help us fully realize personalization—and relevance—at scale. With platforms like Search and YouTube reaching billions of people everyday, digital ad platforms finally can achieve communication at scale. This scale, combined with customization possible through AI, means we’ll soon be able to tailor campaigns to consumer intent in the moment. It will be like having a million planners in your pocket.
Find out how you can achieve relevance at scale. Download now!
More Relevant Stories for Your Company
Datashare for Financial Services: Securing the Publishers and Consumers’ Access to Market Data
Access to the cloud has advanced the distribution and consumption of financial information on a global scale. In parallel, the global financial data landscape has been transformed by an influx of alternative data sources, including social media, meteorological data, satellite imagery, and other data. Exchanges and market data providers now
New Technology: The Projected Total Economic Impact™ Of Google Cloud Contact Center AI
According to Forrester Research, customers expect easy and effective customer service that builds positive emotional connections every time they interact with a brand or organization. Additionally, 40% of surveyed business leaders say that improving their organization’s customer experience (CX) is a high priority, ahead of initiatives like improving products and
Upgrade Your Contact Center with Knowlarity’s AI-powered Speech Analytics for Higher CX
Did you know, everyday about 56 million hours worth of phone conversations, equalling to 420 billion spoken words are handled by contact centers? Knowlarity, a renowned cloud business communication service provider with nearly 6,000 customers and over a million virtual users, leverages AI-powered speech analytics that offer insights to gauge
Innovate Faster & More Flexibly: How Our Commitment to Open Source Unlocks AI and ML Innovation
At Google, we believe anyone should be able to quickly and easily turn their artificial intelligence (AI) idea into reality. Open source software (OSS) has become increasingly important to this goal, heavily influencing the pace of innovation in AI and machine learning (ML) ecosystems. Over the last two decades, ML
