Deployment (79)

• How to Successfully Deploy Data Science Projects - Jan 31, 2022.
  
  This guide will provide detailed insight into the steps you can take to successfully manage your data science projects.

  Deployment

• Models Are Rarely Deployed: An Industry-wide Failure in Machine Learning Leadership - Jan 17, 2022.
  
  In this article, Eric Siegel summarizes the recent KDnuggets poll results and argues that the pervasive failure of ML projects comes from a lack of prudent leadership. He also argues that MLops is not the fundamental missing ingredient – instead, an effective ML leadership practice must be the dog that wags the model-integration tail.

  Deployment

• 5 Practical Data Science Projects That Will Help You Solve Real Business Problems for 2022 - Dec 1, 2021.
  
  This curated list of data science projects offers real-life problems that will help you master skills to demonstration that you are technically sound and know how to conduct data science projects that add business value.

  Data Science, Deployment, Project

• New Poll: What Percentage of Your Machine Learning Models Have Been Deployed? - Nov 29, 2021.
  
  Take a moment to participate in the latest KDnuggets poll and let the community know what percentage of your machine learning models have been deployed.

  Deployment, Poll, Production, Success

• Accelerating AI with MLOps - Nov 24, 2021.
  
  Companies are racing to use AI, but despite its vast potential, most AI projects fail. Examining and resolving operational issues upfront can help AI initiatives reach their full potential.

  AI, Deployment, MLOps

• AI Infinite Training & Maintaining Loop - Nov 4, 2021.
  
  Productizing AI is an infrastructure orchestration problem. In planning your solution design, you should use continuous monitoring, retraining, and feedback to ensure stability and sustainability.

  AI, Deployment, Machine Learning, Production, Training

• How to Build Data Frameworks with Open Source Tools to Enhance Agility and Security - Oct 27, 2021.
  
  Let’s take a look at how to harness open source tools to build your data frameworks.

  Data Democratization, Deployment, Open Source, Security

• Machine Learning Model Development and Model Operations: Principles and Practices - Oct 27, 2021.
  
  The ML model management and the delivery of highly performing model is as important as the initial build of the model by choosing right dataset. The concepts around model retraining, model versioning, model deployment and model monitoring are the basis for machine learning operations (MLOps) that helps the data science teams deliver highly performing models.

  Algorithms, Deployment, Feature Engineering, Machine Learning, MLOps

• Deploying Serverless spaCy Transformer Model with AWS Lambda - Oct 22, 2021.
  
  A step-by-step guide on how to deploy NER transformer model serverless.

  AWS, Deployment, NLP, spaCy, Transformer

• Deploying Your First Machine Learning API - Oct 14, 2021.
  
  Effortless way to develop and deploy your machine learning API using FastAPI and Deta.

  API, Deployment, FastAPI, Machine Learning, Python, spaCy

• Building and Operationalizing Machine Learning Models: Three tips for success - Oct 7, 2021.
  
  With more enterprises implementing machine learning to improve revenue and operations, properly operationalizing the ML lifecycle in a holistic way is crucial for data teams to make their projects efficient and effective.

  Deployment, Machine Learning, Machine Learning Engineer, Tips

• MLOps And Machine Learning Roadmap - Aug 12, 2021.
  
  A 16–20 week roadmap to review machine learning and learn MLOps.

  Courses, DataRobot, Deployment, DevOps, Kubeflow, Kubernetes, Machine Learning, Microsoft Azure, MLOps

• ColabCode: Deploying Machine Learning Models From Google Colab - Jul 22, 2021.
  
  New to ColabCode? Learn how to use it to start a VS Code Server, Jupyter Lab, or FastAPI.

  Deployment, FastAPI, Google Colab, Machine Learning, Python

• When to Retrain an Machine Learning Model? Run these 5 checks to decide on the schedule - Jul 20, 2021.
  
  Machine learning models degrade with time, and need to be regularly updated. In the article, we suggest how to approach retraining and plan for it in advance.

  Data Science, Deployment, Machine Learning, MLOps

• MLOps is an Engineering Discipline: A Beginner’s Overview - Jul 8, 2021.
  
  MLOps = ML + DEV + OPS. MLOps is the idea of combining the long-established practice of DevOps with the emerging field of Machine Learning.

  Data Engineering, Deployment, Machine Learning, MLOps, Modeling

• The only Jupyter Notebooks extension you truly need - Jun 8, 2021.
  
  Now you don’t need to restart the kernel after editing the code in your custom imports.

  Deployment, Jupyter, Machine Learning, Python

• Supercharge Your Machine Learning Experiments with PyCaret and Gradio - May 31, 2021.
  
  A step-by-step tutorial to develop and interact with machine learning pipelines rapidly.

  Deployment, Machine Learning, Pipeline, PyCaret, Python

• Topic Modeling with Streamlit - May 26, 2021.
  
  What does it take to create and deploy a topic modeling web application quickly? Read this post to see how the author uses Python NLP packages for topic modeling, Streamlit for the web application framework, and Streamlit Sharing for deployment.

  Deployment, NLP, Python, spaCy, Streamlit, Text Analytics, Topic Modeling

• Deploy a Dockerized FastAPI App to Google Cloud Platform - May 4, 2021.
  
  A short guide to deploying a Dockerized Python app to Google Cloud Platform using Cloud Run and a SQL instance.

  API, Deployment, Docker, FastAPI, Google Cloud

• How to Dockerize Any Machine Learning Application - Apr 6, 2021.
  
  How can you -- an awesome Data Scientist -- also be known as an awesome software engineer? Docker. And these 3 simple steps to use it for your solutions over and over again.

  Advice, Applications, Containers, Deployment, Docker, Machine Learning

• How to deploy Machine Learning/Deep Learning models to the web - Apr 5, 2021.
  
  The full value of your deep learning models comes from enabling others to use them. Learn how to deploy your model to the web and access it as a REST API, and begin to share the power of your machine learning development with the world.

  Deep Learning, Deployment, Machine Learning, RESTful API

• Overview of MLOps - Mar 26, 2021.
  
  Building a machine learning model is great, but to provide real business value, it must be made useful and maintained to remain useful over time. Machine Learning Operations (MLOps), overviewed here, is a rapidly growing space that encompasses everything required to deploy a machine learning model into production, and is a crucial aspect to delivering this sought after value.

  Data Science, Deployment, Machine Learning, MLOps, Monitoring

• A Machine Learning Model Monitoring Checklist: 7 Things to Track - Mar 11, 2021.
  
  Once you deploy a machine learning model in production, you need to make sure it performs. In the article, we suggest how to monitor your models and open-source tools to use.

  Checklist, Data Science, Deployment, Machine Learning, MLOps, Monitoring

• Machine Learning Systems Design: A Free Stanford Course - Feb 26, 2021.
  
  This freely-available course from Stanford should give you a toolkit for designing machine learning systems.

  Courses, Deployment, Design, Machine Learning, Maintenance, Stanford

• One question to make your data project 10x more valuable - Feb 1, 2021.
  
  If you are the "data person" for your organization, then providing meaningful results to stakeholder data requests can sometimes feel like shots in the dark. However, you can make sure your data analysis is actionable by asking one magic question before getting started.

  Advice, Business, Data Analysis, Data Mining, Data Science, Deployment, Problem Definition

• 8 New Tools I Learned as a Data Scientist in 2020 - Jan 14, 2021.
  
  The author shares the data science tools learned while making the move from Docker to Live Deployments.

  Data Science, Data Science Tools, Data Scientist, Deployment, Docker, Kubernetes, MLflow, NoSQL

• 10 Underappreciated Python Packages for Machine Learning Practitioners - Jan 7, 2021.
  
  Here are 10 underappreciated Python packages covering neural architecture design, calibration, UI creation and dissemination.

  Deployment, Neural Networks, Python, UI/UX

• Data Science as a Product – Why Is It So Hard? - Dec 30, 2020.
  
  Developing machine learning models as products that deliver business value remains a new field with uncharted paths toward success. Applying well-established software development approaches, such as agile, is not straightforward, but may still offer a solid foundation to guide success.

  Agile, Data Science, Deployment, Product

• Production Machine Learning Monitoring: Outliers, Drift, Explainers & Statistical Performance - Dec 21, 2020.
  
  A practical deep dive on production monitoring architectures for machine learning at scale using real-time metrics, outlier detectors, drift detectors, metrics servers and explainers.

  AI, Deployment, Explainable AI, Machine Learning, Modeling, Outliers, Production, Python

• MLOps Is Changing How Machine Learning Models Are Developed - Dec 21, 2020.
  
  Delivering machine learning solutions is so much more than the model. Three key concepts covering version control, testing, and pipelines are the foundation for machine learning operations (MLOps) that help data science teams ship models quicker and with more confidence.

  Deployment, Machine Learning, MLOps

• Deploying Trained Models to Production with TensorFlow Serving - Nov 30, 2020.
  
  TensorFlow provides a way to move a trained model to a production environment for deployment with minimal effort. In this article, we’ll use a pre-trained model, save it, and serve it using TensorFlow Serving.

  Deployment, Modeling, Neural Networks, Python, TensorFlow

• AI Is More Than a Model: Four Steps to Complete Workflow Success - Nov 17, 2020.
  
  The key element for success in practical AI implementation is uncovering any issues early on and knowing what aspects of the workflow to focus time and resources on for the best results—and it’s not always the most obvious steps.

  AI, Data Preparation, Data Science Process, Deployment, MathWorks, Simulation, Workflow

• How to deploy PyTorch Lightning models to production - Nov 5, 2020.
  
  A complete guide to serving PyTorch Lightning models at scale.

  Deployment, Neural Networks, Production, Python, PyTorch, PyTorch Lightning

• Building Deep Learning Projects with fastai — From Model Training to Deployment - Nov 4, 2020.
  
  A getting started guide to develop computer vision application with fastai.

  Deep Learning, Deployment, fast.ai, Modeling, Python, Training

• Deploying Secure and Scalable Streamlit Apps on AWS with Docker Swarm, Traefik and Keycloak - Oct 23, 2020.
  
  If you are a data scientist who just wants to get the work done but doesn’t necessarily want to go down the DevOps rabbit hole, this tutorial offers a relatively straightforward deployment solution leveraging Docker Swarm and Traefik, with an option of adding user authentication with Keycloak.

  AWS, Deployment, Docker, Scalability, Security, Streamlit

• Deploying Streamlit Apps Using Streamlit Sharing - Oct 20, 2020.
  
  Read this sneak peek into Streamlit’s new deployment platform.

  Deployment, Python, Streamlit

• 6 Lessons Learned in 6 Months as a Data Scientist - Oct 8, 2020.
  
  When transitioning into a Data Science career, a new mindset toward collaboration, data, and reporting is required. Learn from these recommendations on approaches you should consider to successfully develop into your dream job.

  arXiv, Business, Career Advice, Data Scientist, Deployment, GitHub, Podcast

• 5 Challenges to Scaling Machine Learning Models - Oct 7, 2020.
  
  ML models are hard to be translated into active business gains. In order to understand the common pitfalls in productionizing ML models, let’s dive into the top 5 challenges that organizations face.

  Deployment, Machine Learning, Scalability

• Machine Learning Model Deployment - Sep 30, 2020.
  
  Read this article on machine learning model deployment using serverless deployment. Serverless compute abstracts away provisioning, managing severs and configuring software, simplifying model deployment.

  Cloud, Deployment, Machine Learning, Modeling, Workflow

• Create and Deploy your First Flask App using Python and Heroku - Sep 25, 2020.
  
  Flask is a straightforward and lightweight web application framework for Python applications. This guide walks you through how to write an application using Flask with a deployment on Heroku.

  App, Deployment, Flask, Heroku, Python

• Unpopular Opinion – Data Scientists Should Be More End-to-End - Sep 17, 2020.
  
  Can a do-it-all Data Scientist really be more effective at delivering new value from data? While it might sound exhausting, important efficiencies can exist that might bring better value to the business even faster.

  Career Advice, Data Science Process, Data Scientist, Deployment

• Here’s what you need to look for in a model server to build ML-powered services - Sep 15, 2020.
  
  More applications are being infused with machine learning while MLOps processes and best practices are becoming well established. Critical to these software and systems are the servers that run the models, which should feature key capabilities to drive successful enterprise-scale productionizing of machine learning.

  Deployment, Life Cycle, MLOps, Model Drift, Model Performance, Monitoring, Production, Scalability

• Rapid Python Model Deployment with FICO Xpress Insight - Aug 20, 2020.
  
  The biggest hurdle in the use of data to create business value, is indeed the ability to operationalize analytics throughout the organization. Xpress Insight is geared to reduce the burden on IT and address their critical requirements while empowering business users to take ownership of decisions and change management.

  AI, Deployment, FICO, Machine Learning, Optimization, Python

• Why would you put Scikit-learn in the browser? - Jul 22, 2020.
  
  Honestly? I don’t know. But I do think WebAssembly is a good target for ML/AI deployment (in the browser and beyond).

  Deployment, Development, scikit-learn, Virtualization

• Stop training more models, start deploying them - Jun 30, 2020.
  
  We are hardly living up to the promises of AI in healthcare. It’s not because of our training, it’s because of our deployment.

  Deployment, Modeling, Training

• 4 Steps to ensure your AI/Machine Learning system survives COVID-19 - Apr 17, 2020.
  
  Many AI models rely on historical data to make predictions on future behavior. So, what happens when consumer behavior across the planet makes a 180 degree flip? Companies are quickly seeing less value from some AI systems as training data is no longer relevant when user behaviors and preferences change so drastically. Those who are flexible can make it through this crisis in data, and these four techniques will help you stay in front of the competition.

  AI, Coronavirus, COVID-19, Deployment, Machine Learning

• Peer Reviewing Data Science Projects - Apr 13, 2020.
  
  In any technical development field, having other practitioners review your work before shipping code off to production is a valuable support tool to make sure your work is error-proof. Even through your preparation for the review, improvements might be discovered and then other issues that escaped your awareness can be spotted by outsiders. This peer scrutiny can also be applied to Data Science, and this article outlines a process that you can experiment with in your team.

  Advice, Checklist, Data Science, Deployment, KPI

• Software Interfaces for Machine Learning Deployment - Mar 11, 2020.
  
  While building a machine learning model might be the fun part, it won't do much for anyone else unless it can be deployed into a production environment. How to implement machine learning deployments is a special challenge with differences from traditional software engineering, and this post examines a fundamental first step -- how to create software interfaces so you can develop deployments that are automated and repeatable.

  API, Deployment, Machine Learning, MLOps, Software Engineering

• How Kubeflow Can Add AI to Your Kubernetes Deployments - Feb 21, 2020.
  
  As Kubernetes is capable of working with other solutions, it is possible to integrate it with a collection of tools that can almost fully automate your development pipeline. Some of those third-party tools even allow you to integrate AI into Kubernetes. One such tool you can integrate with Kubernetes is Kubeflow. Read more about it here.

  AI, Deployment, Kubernetes

• Scaling the Wall Between Data Scientist and Data Engineer - Feb 17, 2020.
  
  The educational and research focuses of machine learning tends to highlight the model building, training, testing, and optimization aspects of the data science process. To bring these models into use requires a suite of engineering feats and organization, a standard for which does not yet exist. Learn more about a framework for operating a collaborative data science and engineering team to deploy machine learning models to end-users.

  Advice, Data Engineer, Data Engineering, Data Scientist, Deployment, DevOps, Machine Learning Engineer, MLflow, MLOps, Production

• What Does it Mean to Deploy a Machine Learning Model? - Feb 14, 2020.
  
  You are a Data Scientist who knows how to develop machine learning models. You might also be a Data Scientist who is too afraid to ask how to deploy your machine learning models. The answer isn't entirely straightforward, and so is a major pain point of the community. This article will help you take a step in the right direction for production deployments that are automated, reproducible, and auditable.

  Deployment, Machine Learning, MLOps

• Why are Machine Learning Projects so Hard to Manage? - Feb 3, 2020.
  
  What makes deploying a machine learning project so difficult? Is it the expectations? The people? The tech? There are common threads to these challenges, and best practices exist to deal with them.

  Deployment, Kaggle, Lukas Biewald, Machine Learning, Project Fail, Training Data

• Top 5 must-have Data Science skills for 2020 - Jan 8, 2020.
  
  The standard job description for a Data Scientist has long highlighted skills in R, Python, SQL, and Machine Learning. With the field evolving, these core competencies are no longer enough to stay competitive in the job market.

  2020 Predictions, Agile, Cloud Computing, Data Science Skills, Deep Learning, Deployment, GitHub, NLP

• The Ultimate Guide to Model Retraining - Dec 16, 2019.
  
  Once you have deployed your machine learning model into production, differences in real-world data will result in model drift. So, retraining and redeploying will likely be required. In other words, deployment should be treated as a continuous process. This guide defines model drift and how to identify it, and includes approaches to enable model training.

  Deployment, Machine Learning, Model Drift, Model Performance, Monitoring, Production, Training Data

• Deploying a pretrained GPT-2 model on AWS - Dec 12, 2019.
  
  This post attempts to summarize my recent detour into NLP, describing how I exposed a Huggingface pre-trained Language Model (LM) on an AWS-based web application.

  AWS, Deployment, GPT-2, Natural Language Generation, NLP

• Deployment of Machine learning models using Flask - Dec 10, 2019.
  
  This blog will explain the basics of deploying a machine learning algorithm, focusing on developing a Naïve Bayes model for spam message identification, and using Flask to create an API for that model.

  Deployment, Flask, Machine Learning

• Moving Predictive Maintenance from Theory to Practice - Dec 9, 2019.
  
  Here are four common hurdles that need to be overcome before tapping into the benefits of predictive maintenance.

  Deployment, Machine Learning, MathWorks, MATLAB, Predictive Maintenance, Simulation

• An Eight-Step Checklist for An Analytics Project - Nov 6, 2019.
  
  Follow these eight headings of an audit sheet that business analysts should address before submitting the results of their analytics project. One recommended approach is to rewrite each step as a question, answer it, and then attach it to your project.

  Analytics, Checklist, Deployment, Feature Selection, Statistics

• Why is Machine Learning Deployment Hard? - Oct 29, 2019.
  
  Developing an excellent machine learning model is one thing. Deploying it to production is another. Consider these lessons learned and recommendations for approaching this important challenge to help ensure value from your AI work.

  Deployment, Machine Learning

• How to Easily Deploy Machine Learning Models Using Flask - Oct 17, 2019.
  
  This post aims to make you get started with putting your trained machine learning models into production using Flask API.

  Deployment, Flask, Machine Learning, Python

• Four questions to help accurately scope analytics engineering project - Oct 9, 2019.
  
  Being really good at scoping analytics projects is crucial for team productivity and profitability. You can consistently deliver on time if you work out the issue first, and these four questions can help you prepare.

  Analytics, Data Engineering, dbt, Deployment

• 5 Fundamental AI Principles - Oct 3, 2019.
  
  While AI may appear magical at times, these five principles will help guide you to avoid pitfalls when leveraging this tech.

  AI, Data Cleaning, Deployment, Training Data

• TensorFlow 2.0: Dynamic, Readable, and Highly Extended - Aug 27, 2019.
  
  With substantial changes coming with TensorFlow 2.0, and the release candidate version now available, learn more in this guide about the major updates and how to get started on the machine learning platform.

  Deep Learning, Deployment, Exxact, TensorFlow

• 6 Key Concepts in Andrew Ng’s “Machine Learning Yearning” - Aug 12, 2019.
  
  If you are diving into AI and machine learning, Andrew Ng's book is a great place to start. Learn about six important concepts covered to better understand how to use these tools from one of the field's best practitioners and teachers.

  AI, Andrew Ng, Best Practices, Deployment, Machine Learning, Metrics, Training Data

• Easily Deploy Deep Learning Models in Production - Aug 1, 2019.
  
  Getting trained neural networks to be deployed in applications and services can pose challenges for infrastructure managers. Challenges like multiple frameworks, underutilized infrastructure and lack of standard implementations can even cause AI projects to fail. This blog explores how to navigate these challenges.

  Deep Learning, Deployment, GPU, Inference, NVIDIA

• Scaling a Massive State-of-the-art Deep Learning Model in Production - Jul 15, 2019.
  
  A new NLP text writing app based on OpenAI's GPT-2 aims to write with you -- whenever you ask. Find out how the developers setup and deployed their model into production from an engineer working on the team.

  Deep Learning, Deployment, NLP, OpenAI, Scalability, Transformer

• Overview of Different Approaches to Deploying Machine Learning Models in Production - Jun 12, 2019.
  
  Learn the different methods for putting machine learning models into production, and to determine which method is best for which use case.

  Deployment, Jupyter, Machine Learning, Production, Training Data

• Why organizations fail in scaling AI and Machine Learning - May 29, 2019.
  
  We explain why AI needs to understand business processes and how the business processes need to be able to change to bring insight from AI into the process.

  AI, Deployment, Failure, Machine Learning, Scalability

• The Four Levels of Analytics Maturity - Mar 26, 2019.
  
  We outline our four-step model to categorize how successfully a company uses analytics by its ability to show the analytics, uncover underlying trends, and take action based on them.

  Analytics, Business, Deployment, Performance, Visualization

• Automatic Machine Learning is broken - Feb 19, 2019.
  
  We take a look at the arguments against implementing a machine learning solution, and the occasions when the problems faced are not ML problems and can perhaps be solved using optimization, exploratory data analysis tasks or problems that can be solved with simple statistics.

  Automated Machine Learning, AutoML, Data Preparation, Deployment

• How to Monitor Machine Learning Models in Real-Time - Jan 18, 2019.
  
  We present practical methods for near real-time monitoring of machine learning systems which detect system-level or model-level faults and can see when the world changes.

  Anomaly Detection, Deployment, Machine Learning, MapR, Monitoring, Real-time

• Self-Service Analytics and Operationalization – Why You Need Both - Nov 12, 2018.
  
  Get the guidebook / whitepaper for a look at how today's top data-driven companies scale their advanced analytics & machine learning efforts.

  Analytics, Data Science, Dataiku, Deployment, Self-service

• Building a Machine Learning Model through Trial and Error - Sep 24, 2018.
  
  A step-by-step guide that includes suggestions on how to preprocess data and deriving features from this. This article also contains links to help you explore additional resources about machine learning methods and other examples.

  Deployment, Machine Learning, MathWorks

• 9 Reasons why your machine learning project will fail - Jul 25, 2018.
  
  This article explains in detail some of the issues that you may face during your machine learning project.

  Deployment, Failure, Machine Learning, Project Fail

• Data Science: 4 Reasons Why Most Are Failing to Deliver - May 24, 2018.
  
  Data Science: Some see billions in returns, but most are failing to deliver. This article explores some of the reasons why this is the case.

  Data Science, Deployment, Domino, Failure, Production

• An ode to the analytics grease monkeys - Feb 2, 2017.
  
  Analytics is not one time job. It needs to be automated, deployed and improved for future business analytics requirements. Here an IBM expert discusses about development & deployment of analytics assets and capabilities of it.

  Analytics, Analytics Leader, CRISP-DM, Deployment, IBM, IBM DSX, ROI

• Continuous improvement for IoT through AI / Continuous learning - Nov 25, 2016.
  
  In reality, especially for IoT, it is not like once an analytics model is built, it will give the results with same accuracy till the end of time. Data pattern changes over the time which makes it absolutely important to learn from new data and improve/recalibrate the models to get correct result. Below article explain this phenomenon of continuous improvement in analytics for IoT.

  AI, Deployment, IoT, Machine Learning, Model Performance, Realtime Analytics

• Questions To Ask When Moving Machine Learning From Practice to Production - Nov 18, 2016.
  
  An overview of applying machine learning techniques to solve problems in production. This articles covers some of the varied questions to ponder when incorporating machine learning into teams and processes.

  Data Science, Deep Learning, Deployment, Machine Learning, Production

• Streamlining Analytic Deployment: Inside the FICO Decision Management Suite 2.0 - Jul 8, 2016.
  
  This post explains what’s new in the 2.0 version of the FICO Decision Management Suite, and how it can be used by data scientists and others to create stronger customer relationships and provide strategic competitive advantage.

  Decision Management, Decision Support, Deployment, FICO