{"id":2017,"date":"2018-08-28T12:30:04","date_gmt":"2018-08-28T12:30:04","guid":{"rendered":"http:\/\/capture.ccio.us\/?p=2017"},"modified":"2018-08-28T12:57:45","modified_gmt":"2018-08-28T12:57:45","slug":"everyone-ga-ga-amazons-recommendations-engine-except-apparently","status":"publish","type":"post","link":"https:\/\/capture.club\/portal\/2018\/08\/28\/everyone-ga-ga-amazons-recommendations-engine-except-apparently\/","title":{"rendered":"Why is Everyone Ga-Ga for Amazon’s Recommendations Engine?"},"content":{"rendered":"

<\/p>\u00a0\n

\"Amazon — Everyone Thinks Amazon\u2019s Recommendation Engine is all that, but it\u2019s really not.<\/figcaption><\/figure>\n
I talk to people about Machine Learning<\/a> and Predictive Analytics<\/a> everyday. During the course of that conversation, the topic of Amazon\u2019s Amazing Recommendations generally comes up as an example of the Gold Standard of recommendation engines.<\/p>\n
But you know what? I really don\u2019t think so.<\/p>\n
As I was browsing around Amazon<\/a> the other day, I noticed some slipper recommendations at the bottom of the page, based on my previous purchase history.\u00a0 Okay, great!<\/p>\n
$\"\"$ <\/p>\n
\u00a0<\/p>\n
So I click on a pair that looks interesting, and check the sizing available:<\/p>\n
$\"\"$ <\/p>\n
\u00a0<\/p>\n
Now footwear, where I am concerned, is a bit of a challenge.\u00a0 I have a 14 EEE shoe size, which seems to be harder and harder to come by these days.\u00a0 Thus I\u2019m always on the lookout for something that suits my style, and that will fit comfortably.<\/p>\n
It can be a challenge, let me tell you.<\/p>\n
So when I saw these slippers in my recommendations, I thought: \u201cGreat!\u201d and I clicked on them, and checked the sizes.\u00a0 While they did indeed have a 14D, there was no 14EEE.<\/p>\n
And thus my question:\u00a0 If I have been buying 14EEE shoes at Amazon for years, why is it showing me shoes that do not come in my size, despite the fact that it knows my size quite well, and the NoSQL nature of it\u2019s dataset certainly lends itself to such predictive results.\u00a0 So why do I not see these results?<\/p>\n
The answer is pretty simple, really:\u00a0 They\u2019re not mining these types of attributes for the recommendations, although they certainly could do so.<\/p>\n
I was teaching a Machine Learning course to Verizon a couple months ago, and the subject of Amazon\u2019s recommendation\u00a0 engine came up.\u00a0 \u00a0I could see the light in the eyes of the engineer\u2019s as they spoke with near hushed tones about the invulnerability of Amazon\u2019s recommendations.\u00a0 \u00a0As the discussion progressed, we started talking about what types of data can be used to predict accurate recommendations.\u00a0 The list is long.\u00a0 Longer than you might think, and actually becomes quite granular as you consider the data in greater detail.<\/p>\n
The bottom line is this:\u00a0 Amazon knows what style of shoe (or slipper) I prefer, and it knows the size that I **always<\/strong><\/em> buy.\u00a0 It should, in theory, be showing me only those slippers that at the very least<\/u> come in my size.<\/p>\n**
**So when you are confronted with the fact that your sites recommendations are not as good as Amazon, fret not.\u00a0 You can beat them.<\/p>\n**
**Just drill a bit deeper into your data; the genotype you create from a product can be very tightly matched to a customer\u2019s preferences.<\/p>\n**
**\u00a0<\/p>\n**
**\u00a0<\/p>\n<\/body>","protected":false},"excerpt":{"rendered":"**
\u00a0 I talk to people about Machine Learning and Predictive Analytics everyday. During the course of that conversation, the topic of Amazon\u2019s Amazing Recommendations generally comes up as an example of the Gold Standard of recommendation engines. But you know what? I really don\u2019t think so. As I was browsing around Amazon the other day, […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"pagelayer_contact_templates":[],"_pagelayer_content":"","footnotes":""},"categories":[],"tags":[],"class_list":["post-2017","post","type-post","status-publish","format-standard","hentry"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/posts\/2017","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/comments?post=2017"}],"version-history":[{"count":0,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/posts\/2017\/revisions"}],"wp:attachment":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/media?parent=2017"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/categories?post=2017"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/tags?post=2017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}

Everyone Thinks Amazon\u2019s Recommendation Engine is all that, but it\u2019s really not.<\/figcaption><\/figure>\n
I talk to people about Machine Learning<\/a> and Predictive Analytics<\/a> everyday. During the course of that conversation, the topic of Amazon\u2019s Amazing Recommendations generally comes up as an example of the Gold Standard of recommendation engines.<\/p>\n
But you know what? I really don\u2019t think so.<\/p>\n
As I was browsing around Amazon<\/a> the other day, I noticed some slipper recommendations at the bottom of the page, based on my previous purchase history.\u00a0 Okay, great!<\/p>\n
$\"\"$ <\/p>\n
\u00a0<\/p>\n
So I click on a pair that looks interesting, and check the sizing available:<\/p>\n
$\"\"$ <\/p>\n
\u00a0<\/p>\n
Now footwear, where I am concerned, is a bit of a challenge.\u00a0 I have a 14 EEE shoe size, which seems to be harder and harder to come by these days.\u00a0 Thus I\u2019m always on the lookout for something that suits my style, and that will fit comfortably.<\/p>\n
It can be a challenge, let me tell you.<\/p>\n
So when I saw these slippers in my recommendations, I thought: \u201cGreat!\u201d and I clicked on them, and checked the sizes.\u00a0 While they did indeed have a 14D, there was no 14EEE.<\/p>\n
And thus my question:\u00a0 If I have been buying 14EEE shoes at Amazon for years, why is it showing me shoes that do not come in my size, despite the fact that it knows my size quite well, and the NoSQL nature of it\u2019s dataset certainly lends itself to such predictive results.\u00a0 So why do I not see these results?<\/p>\n
The answer is pretty simple, really:\u00a0 They\u2019re not mining these types of attributes for the recommendations, although they certainly could do so.<\/p>\n
I was teaching a Machine Learning course to Verizon a couple months ago, and the subject of Amazon\u2019s recommendation\u00a0 engine came up.\u00a0 \u00a0I could see the light in the eyes of the engineer\u2019s as they spoke with near hushed tones about the invulnerability of Amazon\u2019s recommendations.\u00a0 \u00a0As the discussion progressed, we started talking about what types of data can be used to predict accurate recommendations.\u00a0 The list is long.\u00a0 Longer than you might think, and actually becomes quite granular as you consider the data in greater detail.<\/p>\n
The bottom line is this:\u00a0 Amazon knows what style of shoe (or slipper) I prefer, and it knows the size that I **always<\/strong><\/em> buy.\u00a0 It should, in theory, be showing me only those slippers that at the very least<\/u> come in my size.<\/p>\n**
**So when you are confronted with the fact that your sites recommendations are not as good as Amazon, fret not.\u00a0 You can beat them.<\/p>\n**
**Just drill a bit deeper into your data; the genotype you create from a product can be very tightly matched to a customer\u2019s preferences.<\/p>\n**
**\u00a0<\/p>\n**
**\u00a0<\/p>\n<\/body>","protected":false},"excerpt":{"rendered":"**
\u00a0 I talk to people about Machine Learning and Predictive Analytics everyday. During the course of that conversation, the topic of Amazon\u2019s Amazing Recommendations generally comes up as an example of the Gold Standard of recommendation engines. But you know what? I really don\u2019t think so. As I was browsing around Amazon the other day, […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"om_disable_all_campaigns":false,"pagelayer_contact_templates":[],"_pagelayer_content":"","footnotes":""},"categories":[],"tags":[],"class_list":["post-2017","post","type-post","status-publish","format-standard","hentry"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/posts\/2017","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/comments?post=2017"}],"version-history":[{"count":0,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/posts\/2017\/revisions"}],"wp:attachment":[{"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/media?parent=2017"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/categories?post=2017"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/capture.club\/portal\/wp-json\/wp\/v2\/tags?post=2017"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}