{"id":7282,"date":"2020-06-19T08:33:52","date_gmt":"2020-06-19T08:33:52","guid":{"rendered":"https:\/\/www.price2spy.com\/blog\/?p=7282"},"modified":"2020-06-19T12:49:25","modified_gmt":"2020-06-19T12:49:25","slug":"part-2-product-matching-via-machine-learning-important-decisions-to-be-made","status":"publish","type":"post","link":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/","title":{"rendered":"(Part #2) Product matching via Machine Learning &#8211; Important decisions to be made"},"content":{"rendered":"\n<ul class=\"wp-block-list\"><li><a rel=\"noreferrer noopener\" href=\"https:\/\/www.price2spy.com\/en\/pricing\/product-matching.html\" target=\"_blank\">Product matching in Price2Spy<\/a> <\/li><li><strong>Previous topic:<\/strong>  <a rel=\"noreferrer noopener\" href=\"https:\/\/www.price2spy.com\/blog\/part-1-product-matching-via-machine-learning-introduction-to-the-project\/\" target=\"_blank\">(Part #1) Product matching via Machine Learning &#8211; Introduction to the project <\/a><\/li><li><strong>Next topic:<\/strong>  <a href=\"https:\/\/www.price2spy.com\/blog\/part-3-for-ml-experts-why-is-product-matching-so-difficult\/\">(Part #3) Product matching via Machine Learning &#8211;  For ML experts &#8211; why is product matching so difficult? <\/a><\/li><\/ul>\n\n\n\n<p>Before kicking the project off, we had to make some really important decisions regarding the project scope. <\/p>\n\n\n\n<ol class=\"wp-block-list\"><li><strong>Language-specific or universal ML model?<\/strong><\/li><\/ol>\n\n\n\n<ul class=\"wp-block-list\"><li>Of course, one would like his solution to be as broadly applicable as possible.<\/li><li>Language-specific model would probably be more precise but would require training for each language individually. And, preparing a training set, as you will see is a very difficult one<\/li><li>As <a href=\"https:\/\/www.price2spy.com\/\">Price2Spy<\/a> has clients from literally all <a href=\"https:\/\/www.price2spy.com\/en\/solutions\/clients.html\">over the world<\/a>, we would need to cover at least 15 different languages, and some of them written in non-Latin scripts<\/li><\/ul>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"609\" height=\"221\" src=\"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png\" alt=\"language specifics in machine learning\" class=\"wp-image-7283\" srcset=\"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png 609w, https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages-768x278.png 768w\" sizes=\"auto, (max-width: 609px) 100vw, 609px\" \/><\/figure><\/div>\n\n\n\n<ul class=\"wp-block-list\"><li>Pretty often we face situations where competitor A uses English wording of the product, while competitor B goes for the local language. For example iPhone 11 Red vs iPhone<em> 11 Rot. <\/em>Our ML model would need to be ready for such cases<\/li><li><strong>Decision:<\/strong> try to go for a universal solution, by all means <\/li><\/ul>\n\n\n\n<p>2. <strong>Industry-specific or universal ML model?<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>Price2Spy works with <a href=\"https:\/\/www.price2spy.com\/en\/industries\/all-industries.html\">over 25 different industries<\/a>. Preparing 25 training sets to build 25 different ML models seemed like a nightmare.<\/li><\/ul>\n\n\n\n<div class=\"wp-block-image\"><figure class=\"aligncenter size-full\"><img loading=\"lazy\" decoding=\"async\" width=\"474\" height=\"248\" src=\"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/image.png\" alt=\"industries\" class=\"wp-image-7284\" srcset=\"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/image.png 474w, https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/image-768x401.png 768w\" sizes=\"auto, (max-width: 474px) 100vw, 474px\" \/><\/figure><\/div>\n\n\n\n<ul class=\"wp-block-list\"><li>On the other hand, we all know how little similarities there are between the wording of fashion and luxury products, compared to tires or fresh food<\/li><li>Again, the industry-specific model would probably be more precise but would require training for each language individually. And, preparing a training set which is representative enough, as you will see is a very difficult one<\/li><li><strong>Decision:<\/strong> try to go for a universal solution, by all means <\/li><\/ul>\n\n\n\n<p>3. <strong>Matching accuracy<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li>One thing that we have learned in 9 years in this business is that a wrong match is something that we cannot afford to have in Price2Spy. Wrong match =&gt; Wrong pricing decision. Our customers cannot have that =&gt; we cannot have that!<\/li><li>99% matching accuracy is not sufficient. Even if it\u2019s only 1% of wrong matches \u2013 how can the client know which 1% is wrong?<\/li><li>ML is all about math and probability. Even when ML claims that we have a 99% probable match \u2013 that\u2019s not good enough. Humans need to verify this<\/li><li>Fortunately enough, verifying a match takes much less human time that establishing one. So, ML will not fully replace the need for human work \u2013 but it will significantly reduce it while keeping the match quality at 100%<\/li><li><strong>Decision:<\/strong> we\u2019re striving for 100% matching accuracy<\/li><\/ul>\n\n\n\n<p>So, we have our 3 key ML matching decisions. On to the next task \u2013 preparing the training set!<\/p>\n\n\n\n<p><strong>Find more information here:<\/strong><\/p>\n\n\n\n<ul class=\"wp-block-list\"><li><a rel=\"noreferrer noopener\" aria-label=\"Product matching in Price2Spy (opens in a new tab)\" href=\"https:\/\/www.price2spy.com\/en\/pricing\/product-matching.html\" target=\"_blank\">Product matching in Price2Spy<\/a> <\/li><li><strong>Previous topic:<\/strong>  <a rel=\"noreferrer noopener\" aria-label=\"(Part #1) Product matching via Machine Learning - Introduction to the project  (opens in a new tab)\" href=\"https:\/\/www.price2spy.com\/blog\/part-1-product-matching-via-machine-learning-introduction-to-the-project\/\" target=\"_blank\">(Part #1) Product matching via Machine Learning &#8211; Introduction to the project <\/a><\/li><li><strong>Next topic:<\/strong>  <a href=\"https:\/\/www.price2spy.com\/blog\/part-3-for-ml-experts-why-is-product-matching-so-difficult\/\" target=\"_blank\" rel=\"noreferrer noopener\" aria-label=\"(Part #3) Product matching via Machine Learning -  For ML experts - why is product matching so difficult? (opens in a new tab)\">(Part #3) Product matching via Machine Learning &#8211;  For ML experts &#8211; why is product matching so difficult?<\/a> <\/li><\/ul>\n","protected":false},"excerpt":{"rendered":"<p>Product matching in Price2Spy Previous topic: (Part #1) Product matching via Machine Learning &#8211; Introduction to the project Next topic: (Part #3) Product matching via Machine Learning &#8211; For ML experts &#8211; why is product matching so difficult? Before kicking the project off, we had&#8230;<\/p>\n","protected":false},"author":4,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[108,167],"tags":[190,645,646,15,81],"class_list":["post-7282","post","type-post","status-publish","format-standard","hentry","category-best-practices","category-new-price2spy-features","tag-ecommerce","tag-machine-learning","tag-ml","tag-price2spy","tag-product-matching"],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v25.9 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>#2 Product matching via Machine Learning - Important decisions to be made<\/title>\n<meta name=\"description\" content=\"Before kicking the project off, we had to make some really important decisions regarding the Product matching via Machine Learning project.\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"#2 Product matching via Machine Learning - Important decisions to be made\" \/>\n<meta property=\"og:description\" content=\"Before kicking the project off, we had to make some really important decisions regarding the Product matching via Machine Learning project.\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/\" \/>\n<meta property=\"og:site_name\" content=\"Price2Spy\u00ae Blog\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/Price2Spy\/\" \/>\n<meta property=\"article:published_time\" content=\"2020-06-19T08:33:52+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2020-06-19T12:49:25+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png\" \/>\n<meta name=\"author\" content=\"Mi\u0161a Kruni\u0107\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@Price2Spy\" \/>\n<meta name=\"twitter:site\" content=\"@Price2Spy\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Mi\u0161a Kruni\u0107\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"2 minutes\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"#2 Product matching via Machine Learning - Important decisions to be made","description":"Before kicking the project off, we had to make some really important decisions regarding the Product matching via Machine Learning project.","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/","og_locale":"en_US","og_type":"article","og_title":"#2 Product matching via Machine Learning - Important decisions to be made","og_description":"Before kicking the project off, we had to make some really important decisions regarding the Product matching via Machine Learning project.","og_url":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/","og_site_name":"Price2Spy\u00ae Blog","article_publisher":"https:\/\/www.facebook.com\/Price2Spy\/","article_published_time":"2020-06-19T08:33:52+00:00","article_modified_time":"2020-06-19T12:49:25+00:00","og_image":[{"url":"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png","type":"","width":"","height":""}],"author":"Mi\u0161a Kruni\u0107","twitter_card":"summary_large_image","twitter_creator":"@Price2Spy","twitter_site":"@Price2Spy","twitter_misc":{"Written by":"Mi\u0161a Kruni\u0107","Est. reading time":"2 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/","url":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/","name":"#2 Product matching via Machine Learning - Important decisions to be made","isPartOf":{"@id":"https:\/\/www.price2spy.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/#primaryimage"},"image":{"@id":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/#primaryimage"},"thumbnailUrl":"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png","datePublished":"2020-06-19T08:33:52+00:00","dateModified":"2020-06-19T12:49:25+00:00","author":{"@id":"https:\/\/www.price2spy.com\/blog\/#\/schema\/person\/382ac9db90cb7d6dd54b9425857fc96c"},"description":"Before kicking the project off, we had to make some really important decisions regarding the Product matching via Machine Learning project.","breadcrumb":{"@id":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/#primaryimage","url":"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png","contentUrl":"https:\/\/www.price2spy.com\/blog\/wp-content\/uploads\/2020\/06\/languages.png","width":609,"height":221},{"@type":"BreadcrumbList","@id":"https:\/\/www.price2spy.com\/blog\/part-2-product-matching-via-machine-learning-important-decisions-to-be-made\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.price2spy.com\/blog\/"},{"@type":"ListItem","position":2,"name":"(Part #2) Product matching via Machine Learning &#8211; Important decisions to be made"}]},{"@type":"WebSite","@id":"https:\/\/www.price2spy.com\/blog\/#website","url":"https:\/\/www.price2spy.com\/blog\/","name":"Price2Spy\u00ae Blog","description":"Price2Spy\u00ae","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.price2spy.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.price2spy.com\/blog\/#\/schema\/person\/382ac9db90cb7d6dd54b9425857fc96c","name":"Mi\u0161a Kruni\u0107","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.price2spy.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/secure.gravatar.com\/avatar\/31aa4afb2464eca1f1ca0c7979628c87e54e7a6b53ebcb371749e9349d27c850?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/31aa4afb2464eca1f1ca0c7979628c87e54e7a6b53ebcb371749e9349d27c850?s=96&d=mm&r=g","caption":"Mi\u0161a Kruni\u0107"},"description":"Father of 2, Husband of 1, CEO of 3 :-)","sameAs":["http:\/\/www.price2spy.com"],"url":"https:\/\/www.price2spy.com\/blog\/author\/misha\/"}]}},"_links":{"self":[{"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/posts\/7282","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/users\/4"}],"replies":[{"embeddable":true,"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/comments?post=7282"}],"version-history":[{"count":3,"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/posts\/7282\/revisions"}],"predecessor-version":[{"id":7324,"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/posts\/7282\/revisions\/7324"}],"wp:attachment":[{"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/media?parent=7282"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/categories?post=7282"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.price2spy.com\/blog\/wp-json\/wp\/v2\/tags?post=7282"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}