How to Choose the Right ML Model for Your Applications
4875
Of your peers have already read this article.
2:00 Minutes
The most insightful time you'll spend today!
Many of our customers want to know how to choose a technology stack for solving problems with machine learning (ML). There are many choices for these solutions available, some that you can build and some that you can buy. We’ll be focusing on the build side here, exploring the various options and the problems they solve, along with our recommendations.
The best ML applications are trained with the largest amount of data
But first, keep in mind an important concept: the quality of your ML model improves with the size of your data. Dramatic ML performance and accuracy are driven by improvements in data size, as shown in the graph below. This is a text model, but the same principles hold for all kinds of ML models.
The X axis represents the size of the data set and the Y axis is the error rate. As the size of the data set increases, the error rate drops. But notice something critical about the size of the data set — the x-axis is2^20, 2^21, 2^ 22, etc. In other words, each new tic here is a doubling of the data set size. To get a linear decrease in your error rate you need to exponentially increase the size of your data set.
The blue curve in the graph represents a slightly more sophisticated ML model than the orange curve. Suppose you are deciding between two choices: create a better model or double the data set size. Assuming that these two choices cost the same, it’s better to keep gathering more data. It’s only when improvements due to data size increases start to plateau that it becomes necessary to build a better model.
Secondly, ML systems need to be retrained for new situations. For example, if you have a recommendation system in YouTube and you want to provide recommendations in Google Now, you can’t use the same recommendations model. You have to train it in the second instance on the recommendations you want to make in Google Now. So even though the model, the code, and the principles are the same, you have to retrain the model with new data for new situations.
Now, let’s combine these two concepts: you get a better ML model when you have more data, and an ML model typically needs to be retrained for a new situation. You have a choice of either spending your time building an ML model or buying a vendor’s off-the-shelf model.
To answer the question of whether to buy or whether to build, first determine if the buyable model is solving the same problem that you want to solve. Has it been trained on the same input and on similar labels? Let’s say you’re trying to do a product search, and the model has been trained on catalog images as inputs. But you want to do a product search based on users’ mobile phone photographs of the products. The model that was trained on catalog images won’t work on your mobile phone photographs, and you’d have to build a new model.
But let’s say you’re considering a vendor’s translation model that’s been trained on speeches in the European Parliament. If you want to translate similar speeches, the model works well as it uses the same kind of data.
The next question to ask: does the vendor have more data than you do? If the vendor has trained their model on speeches in the European Parliament but you have access to more speech data than they have, you should build. If they have more data, then we recommend buying their model.
Bottom line: buy the vendor’s solution if it’s trained on the same problem and has access to more data than you do.
Technology stack for common ML use cases
If you need to build, what is the technology stack you need? What are the skills your people need to develop? This depends on the type of problem you are solving. There are four broad categories of ML applications: predictive analytics, unstructured data, automation, and personalization. The recommended technology stack for each is slightly different.
Predictive analytics
Predictive analytics includes detecting fraud, predicting click-through rates, and forecasting demand.
Step one: build an enterprise data warehouse
Here, your data set is primarily structured data, so our recommended first step is to store your data in an enterprise data warehouse (EDW). Your EDW is a source of training examples and product histories tracked over time, and can break down silos and gather data from throughout your organization.
Step two: get good at data analytics
Next, you’d build a data culture, get skilled at data analytics, start to build dashboards, and enable data-driven decisions. At this point, you have all of the data and you know which pieces are trustworthy.
Step three: build ML
From your EDW, you can build your models using SQL pipelines. We recommend using BigQuery ML when doing ML with the data in your EDW. If you want to build a more sophisticated model, you can train TensorFlow/Keras models on BigQuery data. A third option is AutoML tables for state-of-the-art accuracy and for building online microservices.
Unstructured data
Examples of how our customers use ML to gain insights from unstructured data include annotating videos, identifying eye diseases, and triaging emails. Unstructured data can include videos, images, natural language, and text. Deep learning has revolutionized the way we do ML on unstructured data, whether you’re looking at language understanding, image classification, or speech-to-text.
For unstructured data, the models you use will employ deep learning. Here, the ROI heavily favors using AutoML. The amount of time that you’d spend trying to create a new ML model from scratch is almost never worth it. You can spend your money more effectively collecting more data than trying to get a slightly better model. Regardless of the type of unstructured data, our recommendation is to use AutoML for small and medium size data sizes.
But AutoML has a limit to scale. At some point, the size of your data set is going to be so large that architecture search is going to get really expensive. At that point, you may want to go to a best-of-breed model with custom retraining from TensorFlow Hub, for example. If you have data sets that are in the millions of examples, you can build your own custom neural network (NN) architectures. But determine if your data set size has started to plateau, by plotting a graph similar to the one at the top of this post. Build a custom NN architecture only after you’ve plateaued, where increasing amounts of data won’t give you a better model.
Automation
Some examples of how customers are using ML for automation include scheduling maintenance, counting retail footfall, and scanning medical forms. The key thing to keep in mind as you pick a technology stack for these problems is that you’re not building just one ML model. If you want to schedule maintenance orwant to reject transactions, for example, you’ll need to train multiple linked models.
Instead of individual models, think in terms of ML pipelines, which you can orchestrate using all of the technologies already mentioned. Then you have three choices for operationalizing, with three levels of sophistication.
- Vertex AI has turnkey serverless training and batch/online predictions. This is what is recommended for a team of data scientists. .
- Deep Learning VM Image, Cloud Run, Cloud Functions or Dataflow feature customized training and batch/online predictions. This is what is recommended if the team consists of data engineers and scientists.
- Vertex AI Pipelines are fully customizable and recommended for organizations with separate ML engineering and data science teams.
When doing automation, the individual models that you chain together into a pipeline will be a mix – some will be prebuilt, some will be customized, and others will be built from scratch. Vertex AI, by providing a unified interface for all these model types, simplifies the operationalization of these models.
Personalization
ML application examples of personalization include customer segmentation, customer targeting, and product recommendations. For personalization, we again recommend using an EDW, because customer segmentation uses structured marketing data. For product recommendations, you will similarly have prior purchases and web logs in your EDW., You can power clustering applications, or recommendation systems like matrix factorization, and create embeddings directly from your EDW for sophisticated recommendation systems.
For specific use cases, choose the technology stack based on your data size and scope. Start with BigQuery ML for its quick, easy matrix factorization approach. Once your application proves viable and you want a slightly better accuracy, then try AutoML recommendations. But once your data set grows beyond the capabilities of AutoML recommendations, consider training your own custom TensorFlow and Keras models.
To summarize, successful ML starts with the question, “Do I build or do I buy?” If an off-the-shelf solution exists that was trained with similar data and with access to more data than you have, then buy it. Otherwise build it, using the technology stack recommended above for the four categories of ML applications.
Learn more about our artificial intelligence (AI) and ML solutions and check out sessions from our Applied ML Summit on-demand.
Partnering with Google Cloud is the Key Behind Recent Healthcare Innovations
8832
Of your peers have already read this article.
2:00 Minutes
The most insightful time you'll spend today!
It’s simply amazing to witness how some of our systems integrators employ Google Cloud solutions to drive innovation in ways we at Google may never have considered—especially in healthcare. According to analyst firm MarketsandMarkets, the market for the Cloud in healthcare is projected to grow 43% between 2020 and 2025 to nearly $65 billion, fueled by the need for better technology infrastructures and faster digital transformation.
Healthcare and life sciences communities are looking to Google Cloud and its Service engagement model partners to improve collaboration and activate the power of medical data. These transformations deliver robust data analytics and bring a much deeper perspective into health epidemics like COVID-19 to help save lives.
In the healthcare and life sciences industry, our Google Cloud partners and customers provide constant energy and inspiration–and are the magic in some key healthcare innovations globally.
Let me show you how they are solving real-world business challenges.
Improving collaboration in Healthcare
Cloudbakers and Comanche County Memorial Hospital transitioned 2,000 employees to Google Workspace to improve collaboration, reduce costs, and increase security. By implementing a system that requires less maintenance while enabling mobile access to data and true collaboration, Comanche County Memorial Hospital saves $175,000 annually on licenses and helps medical professionals spend more time with patients.
“We chose Google Workspace because it cost a quarter of what we were paying previously, offers the kind of modern features that healthcare facilities need, and gave us data security and peace of mind.” —James Wellman, CIO, Comanche County Memorial Hospital
Accessing previously locked down medical data
Google Cloud and Quantiphi supported advances in cloud-based machine learning services to reduce infrastructure costs, unlock new paths of treatment, and dramatically reduce the amount of time it takes to evaluate scanned imagery following a stroke. John Hopkins University BIOS Division has been working on medical imaging to accelerate insights from scans on approximately 500 patients from 2,500 hours to 90 minutes, and lead to more accurate decision-making for brain injury patients that will ultimately improve medical outcomes.
“We’ve aligned closely with the goal of showing that a cloud-based, AI-driven approach is robust and that it can be performed while protecting personal PHI. In terms of costs, the cloud has definitely reduced some of the traditional financial demands of our research.” —Daniel F. Hanley, Jr., M.D., Director, Johns Hopkins University BIOS Division
Improving data access with the flexibility of Google Cloud
With the help of MediaAgility, TRIARQ migrated to Google Cloud to modernize their platform, build new applications, and expand their global footprint. With BigQuery, TRIARQ can now consolidate all transactional data, past and present, into a single location to report on specific insights and predict future data from e-prescriptions to complex revenue-cycle data and value-base analysis.
“The future of this industry will need to be a global one, and we can no longer be stuck in legacy systems if we want to survive. Having a team that is passionate about supporting us in this journey is definitely a plus point.”—Yaw Kwakye, Co-founder and Chief Architect, TRIARQ
Increasing visibility to COVID-19 outbreaks for actionable insights
As part of its response to the COVID-19 pandemic, HCA Healthcare chose to work with Google Cloud and SADA to create a national portal that increases visibility into outbreaks in 3,100 counties across the country in just 8 weeks. Now, the portal generates 30,000 new analytical views each day that can help inform private and public sector decision making for reopenings, closures, hot spots, and many other population health management activities.
“This project required deep knowledge of AI, and consumer-facing platforms, as well as healthcare. Google brought together the ideal combination of product, people, and partners. Google Cloud’s healthcare-specific products along with SADA’s expertise in the healthcare IT space made this partnership the perfect choice to move quickly and intelligently.”—Dr. Edmund Jackson, Chief Data Officer, HCA Healthcare
We’re committed to building the technology, resources, and services through Partner Advantage to help our partners address this opportunity. Looking for a solution focused partner in your region who has achieved Expertise and/or Specialization in your industry? Search our Global Partner Directory. Not yet a Google Cloud partner? Visit Partner Advantage and learn how to become one today!
IBL Education’s GenAI-based chat mentor with Google
885
Of your peers have already read this article.
3:30 Minutes
The most insightful time you'll spend today!
With more than 6 years of experience in building open source and Generative AI in education at scale, ibleducation.com continues to evolve its approach and services. More recently, the company became an education-focused Vertex AI integrator. They provide enterprises and academic institutions with a platform to build, train and securely customize large language models (LLMs) for interactive mentors using Google’s Vertex AI.
“The education industry only recently began understanding the value of Generative AI with open source and the opportunities it presents,” says Miguel Amigot II, Chief Technology Officer at ibleducation.com. “We’re providing the chance to build a new type of learning, mentoring, and analytics platform that gives organizations total control over their training methods, data, and more, without locking into one vendor.”
Organizations large and small, including Fortune 500 companies and leading universities institutions, use ibleducation.com to support their learners, allow educators to develop coursework, and provide engineers with a solid platform to build on.rely on it to power their learning strategies.
Recently, ibleducation.com chose to partner with Google Cloud to improve its platform and scale beyond its base of millions of users.
Harnessing the power of GenAI in education and training
ibleducation.com initially began working with Google Cloud to unify its education data strategy to drive real-time and predictive analytics.
“Google Cloud outperforms others when it comes to maintaining control over algorithms and general data governance,” says Amigot. “We’re fortunate to be able to maintain ownership of our models while maintaining a pay-per-use pricing model. This is critical for our business. It allows our clients to avoid lower-value maintenance tasks, focus on innovation and user experience, and not worry about excessive costs.”
In the past, because of the high costs and need for AI and engineering talent to produce large language models, schools have been unable to take full advantage of open-source education technologies. Together, ibleducation.com and Google Cloud democratize access to AI-enabled tools for educators worldwide.
With a strong analytics and AI foundation, ibleducation.com has been able to personalize, translate, and create education content faster than before. This has been especially effective in improving accessibility, as automated translation and repurposing ensures those with visual and hearing impairments can interact with the content.
“Google Cloud enables us to reduce the total cost of building, running, and maintaining large language models by more than 70%,” says Amigot. “We’ve seen language model hosting costs decrease before, but nothing like this.”
Bringing AI-powered content creation to educators
Vertex AI has been especially useful in creating content, helping ibleducation.com to dramatically scale out its learning materials. Usage-based pricing mixed with an open-source model gives ibleducation.com the resources to support its users in developing evolving, valuable learning experiences to serve people worldwide.
Additionally, Google Cloud powers ibleducation.com’s Generative AI-based mentors, which provides a one-to-one learning experience to students and professionals looking for tailored skills development.
“The mission is to provide educators with a centralized system wherein they can manage everything from indexing data about customer courses to designing and facilitating UI/UX for users’ digital mentors,” says Amigot. “Google Cloud has helped us cover all of these bases.”
ibleducation.com allows users to create virtual mentors that provide personalized teaching, assess student knowledge, guide students through skills and learning paths, and offer robust learning analytics. Text-to-text and speech-to-speech interfaces can be offered over Slack, Discord, text message-based bots, web scripts, and LTI integrations.
“AI Mentor has been a very effective tool for our users because it adapts to the needs of educators and organizations very quickly,” says Amigot. “We’re seeing people use it for teaching assistance, marketing and administration, and a lot more. Vertex AI allows us to have many models for any variety of purposes.”
Looking forward, ibleducation.com is looking to continue taking personalized learning to new heights.
“From a mission standpoint, we want to expand to reach all the organizations not currently served by online education through our platform, analytics, and other AI-powered services,” says Amigot. “Our relationship with Google Cloud is instrumental in achieving our goal to democratize access to next-generation educational capabilities to more communities and organizations around the globe.”
Ready to take the next step? Join our upcoming GenAI workshop for higher education to learn how Google’s AI tools can help education institutions or explore our EdTech solutions to see how you can make education more personal, safe, and accessible with 100+ cutting-edge products.
Customer Voices: How Firms from Across Industries Leverage Google Cloud
DOWNLOAD CASE STUDY14086
Of your peers have already downloaded this article
1:30 Minutes
The most insightful time you'll spend today!
From powering everyday operations and accelerating application innovation, to providing tools for specific business needs and executing on big ideas, to advancing the security of technology solutions, companies from across industries have leveraged Google Cloud for business benefits.
Companies from across industries have turned to Google Cloud for transforming their business, modernizing their infrastructure, and gleaning intelligence from data. For instance:
- Johnson & Johnson achieved a 41% increase in search results from high-quality job applicants, significantly improving the company’s ability to quickly hire top talent.
- Sony Network Communications now processes 10 billion monthly queries faster, which advances data analysis.
- University College Dublin saw significant 6-figure savings by eliminating legacy hardware, software, and maintenance.
And there are many such examples. Read the collection of case studies to find out how companies from across industries and geographies leveraged Google Cloud for measurable business benefits and for solving complex problems.
3417
Of your peers have already watched this video.
3:53 Minutes
The most insightful time you'll spend today!
How Good Are Google’s Vision, Speech, Translation and Natural Language ML APIs?
Many companies want to be able to adopt machine learning and artificial intelligence quickly into their businesses.
But it isn’t always straight-forward and easy. Custom building the models and setting up and maintaining the infrastructure required for an AI project is time-consuming.
That is where Google’s machine learning APIs come into play.
These ready-to-go ML APIs for vision, speech, translation and natural language can be deployed almost immediately. Imagine being able to tell the state of mind of customers who walk into a store (vision API). Or being able to bridge, easily, India’s significant local language challenges (translation API).
In this short video, you’ll see how easy it is to access—and how accurate—Google’s machine learning APIs for vision, speech, translation and natural language processing.
Watch it now and find new ways to improve your business!
5314
Of your peers have already downloaded this article
7:30 Minutes
The most insightful time you'll spend today!
Sure, machine learning is becoming a business imperative, but how does it work in practice—and what are the benefits for IT managers?
That’s the subject of a new step-by-step guide to solving business and IT problems with artificial intelligence and ML, based on insights gathered by IDG Research Services.
Its publication comes at a time when technology departments face growing pressure to embrace these emerging technologies, yet many have questions about how to get started.
It has real-life examples such as the health services company that used ML to reduce support ticket-resolution time from 48 minutes to six.
In another section, a financial services VP explains that cloud-based ML services enable his company to avoid spending money on computing resources that sit idle.
The guide also includes concrete tips for new ML adopters. For example, a real-estate CIO recommends the use of third-party tools that rely on AI and ML technologies, while a financial services VP highlights the challenge and potential of incorporating unstructured data into ML initiatives.
Download the guide now!
More Relevant Stories for Your Company
How Google Helped the Indian Govt Choose Airport Sites: The Inside Story
Setting out a plan for facility locations is a classic challenge for organizations of all shapes and sizes. This is the case for companies around the world—from retailers to governments and corner stores to department stores. But, in India, it's an especially hard problem to crack. Healthy returns and high
Google Cloud’s Med-PaLM 2: Pioneering Ethical AI Solutions for the Medical Domain
Healthcare breakthroughs change the world and bring hope to humanity through scientific rigor, human insight, and compassion. We believe AI can contribute to this, with thoughtful collaboration between researchers, healthcare organizations and the broader ecosystem. Today, we're sharing exciting progress on these initiatives, with the announcement of limited access to
ML Models Built on Google Cloud Solutions Help You Virtually Participate in National Muffin Day!
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.
Candidate360: Google Cloud and Deloitte Product Improves Universities’ Enrollment and Admission Processes
Given the May 1 deadline for students to enroll, colleges and universities have been carefully watching the numbers of students who put down deposits and commit to a school. Like nearly every other sector in the U.S., colleges and universities have been hit hard by the pandemic and economic downturn,
