Contextual 404s
Leveraging Machine Learning and Web Analytics
404
The HTTP 404, 404 Not Found, 404, Page Not Found, or Server Not Found error message is a Hypertext Transfer Protocol (HTTP) standard response code, in computer network communications, to indicate that the browser was able to communicate with a given server, but the server could not find what was requested. (from wiki)
Sources of 404s
- Bad links within the same website (pages, sitemap)
- Paid marketing campaigns
- Bookmarks by customers for the pages that are not valid any more
- Links from third party affiliates like deals, coupons, reviews
- Search engines that drives organic traffic
Problem
Majority of people who reach a 404 will leave the site and will not come back. 404s results in bad user experience and they are less likely to buy from the same site again. Companies spend a lot of money in various online marketing means to bring customers to the website. Bad links to the active promotions for which company is spending money is a serious concern, they should be identified proactively before promotion goes live. 404s that are result of expired promotions can be leveraged to promote relevant content. For example if a customer visited expired TV promotions page, he can be presented with new active TV promotion links.
Considering just cost per click industry benchmarks on the search network, expenditure to drive customers to site can be in the millions.
Machine Learning
Machine learning (ML) is the scientific study of algorithms and statistical models that computer systems use to perform a specific task without using explicit instructions, relying on patterns and inference instead. It is seen as a subset of artificial intelligence. (from wiki)
Web Analytics
Web analytics informs your marketing decisions by collecting, organizing, measuring, and visualizing customer activity on your web and mobile properties. Using insights gained from analytics, you can build, optimize, and deliver experiences that are engaging, relevant, and personal. (from Adobe)
Companies like Adobe and Google provides web analytics solutions. They are so sophisticated that can give data which helps in identifying customer buying patterns and can help in predicting what customers can buy when they are landed on a page.
Contextual 404s
Contextual 404s is feasible for the pages that are live in the past but not active anymore. By feeding the data captured by web analytics like website visits, clicks, conversions to Machine Learning systems, user can be presented with relevant content that gives a better experience to the user. Instead of presenting static content, machine learning can help in presenting dynamic content that has better potential in driving business.
Note: This is just high level idea. One has to do cost benefit and feasibility analysis before investing resources into this. Companies like Amazon may have far more complex solutions.
