So, you have trained your machine learning model. Maybe you’ve built a project that can detect pneumonia in a lung or filter through text. From here, you have to ask yourself:

How do I know this model will succeed? How will it perform in production?

To answer this important question, we need to understand how to evaluate a machine learning model. This is one of the core tasks in a machine learning workflow, and predicting and planning for a model’s success in production can be a daunting task.

Image for post
Image for post

What is Model Evaluation?

Model Evaluation is the process through which we quantify the quality of a system’s predictions. To do this, we measure the newly trained model performance on a new and independent dataset. …

Image for post
Image for post

Hundreds of millions of people willingly spew their opinions in under 280 characters per post and 6,000 times per second. Sentiment analysis on social media platforms such as Twitter are very effective and straightforward way for analysts to gauge consumer reactions to products and services. The use of machine learning is necessary to properly gather consumer reactions. Individuals sifting through tweets ranging from “Where the Buffalo Wild Things Are” to firey, researched political statements can easily get in the noise and twitter void, especially if a business just wants to gauge the attitude towards a particular product or service.

Tweets are 280-character posts that users can share with their followers either publicly or privately. Due to this character limit, tweets are useful for text mining. Sentiment analysis is the process of reading and understanding multiple tweets about a subject and extracting the general reaction to it by the target audience. Organizations that can benefit from creating twitter sentiment analysis projects range from political groups to consumer brands to celebrity influencers to public relations firms. This includes news and media sites that can harness sentiment analysis technology to see the evolving opinions on certain laws, movements, and emerging technology. …

The Skyl team gathered with data scientists and CEO’s this week to chat about the future of AI in the digital media and marketing landscapes. We learned more about the potential use cases for machine learning in these industries, as well as issues that teams run into while creating data science projects.

Image for post
Image for post
Our delicious spread!

Some of the issues that these marketing and media leaders talked about were:

  • The inability for data science teams to properly communicate how timely and costly certain projects are to their managers
  • It is difficult to gather data properly
  • Buying labeled data, creating a project, and finding out that the data is not…

The landscape of artificial intelligence and machine learning has been rapidly evolving over the past few years. Computers teaching themselves to recognize patterns and predict the future feels like a detail in almost every Ray Bradbury novel explicitly stated or not. It feels mystical, unaccessible, and far-fetched. However, machine learning technology is already part of our day-to-day lives. Though the technical aspects of machine learning technology may be impossible to grasp, the most crucial steps that people must take to successfully introduce machine learning technology is far less technical and easy to grasp. Most people know that the key to any successful project is to first define a problem statement. However, a more ML-specific rule is that all projects require a long process for preprocessing data. This is a less technical process than writing code but will impact the outcome and success of your ML project dramatically. …

Since it’s invention, the internet has changed the way we shop, stay entertained, and communicate. eCommerce sites have rendered the Sears catalog obsolete, watching movies is no longer limited to going to the theater, and the structure of a 9–5 is shifting as more employers allow their employees to work from home. The internet has provided a myriad of conveniences and options for shopping, entertainment, and employment. However, unlimited options being readily available has resulted in problems that hurt both businesses and their customers. A single website that sells one specific product such as perfume can have hundreds of options, and there are so many websites for perfume. Contradictory to common sense, a larger number of choices is better for the consumer because they are more likely to find what they want. However, when faced with too many choices, this decision can become complex. …

Kids have panic attacks and corporations tweet self-deprecating jokes. It is no wonder that the United States has seen a shocking increase in depression and suicide rates among young people over the last 20 years. I would personally like to point my finger at the terrifying threat of global warming, college prep preschools, a manifestation of the extremely competitive nature of college admissions, and negligent food scientists who are not even attempting to invent calorie-free french fries. People may not be able to solve some of these problems using technology, but large strides in machine learning and data science can change the way that young people react to and deal with the future. …

Image for post
Image for post

Most parents feel some fear when allowing their young children to navigate the internet unaccompanied. Many games, such as Minecraft, have a chat feature. Most people on the other side of the screen are children of a similar age, however, there is no way to ensure this. In these chatrooms, kids could be chatting with an adult. Unfortunately for children and parents, adults are known to have slightly more colorful vocabularies than children. Most of these applications and games are entirely unmonitored, and parents expose their children to any type of person when they allow them to communicate online. The type of content that children are exposed to when dealing with strangers could be explicit. And even though some games, such as club penguin, have automatic filters, more popular games do not. One of the biggest fears for parents is unsafe language in chatrooms, especially for young children. This may be a barrier to engagement for businesses catered toward young people. …

Increasingly, digesting and reading news has become a standard in our day-to-day lives. Gone are the days when you get a single update in the evening after work while watching television before bed. People are now bombarded with a constant stream of news updates throughout the day, whether they want to be or not. Headlines are splattered over every form of social media, breaking news is sent to us in alerts, and if we ever need to seek out what is happening, it is a search away. However, it is possible to create your own “Google News” app using machine learning. By teaching an algorithm to automatically sort through headlines from the thousands of possible news sites there are, a business can filter through exactly which content it wants. There are multiple reasons a business would want to do this. Maybe, a veterinary clinic wants to automatically keep updating their website with feel-good stories about pets and babies and wild animals. …

The early detection of diseases is crucial in the process of improving a patient’s health. However, this task can be time-consuming and complex, especially since many serious ailments can present themselves as the common cold or the flu in their early stages. The high demand for specialists that are able to discern illnesses causes many issues in early detection of diseases because they are often focused on more high profile cases. …

The year is 2129 and children are no longer taught to read. Every necessary purchase is automated and delivered by Amazon Robots. There are four people left in the United States who still remember what it was like to drive to work, uphill, both ways. These people love to complain that nothing is human, and they dream of the good old days when machine learning just meant an entertainment application recommended a movie.

It is important to understand the process of automation, so that this vision of the future is as unrealistic in our minds as it is in reality. …


Official Account for — — — — — — — — — — — — — — — - Skyl is a scalable, easy-to-use, collaborative SAAS platform to automate end-to-end ML workflow

Get the Medium app

A button that says 'Download on the App Store', and if clicked it will lead you to the iOS App store
A button that says 'Get it on, Google Play', and if clicked it will lead you to the Google Play store