Smart recommendation systems are commonplace across consumer sites like Amazon, Netflix and Facebook. But how do they compare with recommendations from a trusted human?

In this episode of the GoodPractice Podcast, Ross G and Owen are joined by Filtered's Marc Zao-Sanders to discuss some of the difficulties around machine recommendations and their place in learning.

If you want to share your thoughts on the show, you can tweet us @RossGarnerGP, @OwenFerguson and @MarcZaoSanders.

To find out more about GoodPractice, visit goodpractice.com or tweet us @GoodPractice and @GoodPracticeAus.

The Tim Harford blog that Ross suggested (literally a list of recommendations) can be found at: http://timharford.com/2018/04/understanding-algorithms/

If you're interested in 'hardening', check out: https://www.rhs.org.uk/Advice/profile?PID=386

The Washington Post article Owen discussed is at: https://www.washingtonpost.com/news/speaking-of-science/wp/2018/05/04/one-space-between-each-sentence-they-said-science-just-proved-them-wrong-2

And Ross' Guardian story about Sainsbury's can be found at: https://www.theguardian.com/business/2018/may/06/rotten-results-sainburys-drops-project-to-halve-food-waste