here <\/a>on CoLab, in case you want just to review it there.<\/p>\n\n\n\nSome comments<\/h2>\n\n\n\n The amount of data related to market breadth comes from 1972, the one from DIX and GEX only since 2011, and VIX from 1990. I have doubts about the impact of this lack of data.<\/p>\n\n\n\nThe correlation of data, we can see that there is few correlation between DIX, GEX, VIX and the rest of the data. I’m not sure about the root cause: just because there is not correlation, if there is impact because the difference of amount of data, or any other reason.<\/p>\n\n\n\nI have transformed all data in relative data from one day to other, so in this way I focus on daily changes of all features.<\/p>\n\n\n\nFrom the 10 models I run the one with less MAE is the #7:<\/p>\n\n\n\nPlotly library is much better than seaborn or matplotlib. You can add a lot of visual features that enable you to have a more interactive charts. Blue line is actual S&P 500 value, the red line is the prediction (in terms of change.)<\/p>\n\n\n\nThe accuracy is good for the period where S&P 500 is stable, you can see that during March 2020 you can differentiate the blue and red line better.<\/p>\n\n\n\nThe zoom helps to visually detect when there error is higher:<\/p>\n\n\n\nI have calculated the difference between the actual SPX daily return and the predicted data, my purpose is to add accurate to the prediction when evaluating the TP, FP, TN, FN.<\/p>\n\n\n\nLet’s check the performance of the prediction: True Positive, False Positive, True Negative and False Negative.<\/p>\n\n\n\nFinal thoughts<\/h2>\n\n\n\n I have to continue learning about the different models and how their behavior is.<\/p>\n\n\n\n
I already have seen how to take this basic model and do the traditional backtesting that is done on every quantitative trading system, so I can try to get a more realistic conclusion about the results.<\/p>\n\n\n\n
I have to find the way to add more data in an automatic way, and play with other values that enable me to find more correlations.<\/p>\n\n\n\n
So many things to learn in front of me.<\/p>\n\n\n\n
Please in case you have any feedback, glad to read about it.<\/p>\n","protected":false},"excerpt":{"rendered":"
This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions Shift(-1) have been removed for the SPX price, I consider is an error to add it. I have added data related to DIX, GEX (since 2011) and VIX (since … Read more<\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[151,105],"tags":[],"class_list":["post-5639","post","type-post","status-publish","format-standard","hentry","category-machine-learning","category-trading"],"yoast_head":"\nLooking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX. -<\/title>\n<meta name=\"description\" content=\"This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions - joapen projects\" \/>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX. -\" \/>\n<meta property=\"og:description\" content=\"This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions - joapen projects\" \/>\n<meta property=\"og:url\" content=\"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/\" \/>\n<meta property=\"og:site_name\" content=\"joapen projects\" \/>\n<meta property=\"article:published_time\" content=\"2021-06-10T07:37:31+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2021-06-10T07:37:38+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png\" \/>\n<meta name=\"author\" content=\"joapen\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"joapen\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"4 minutes\" \/>\n<script type=\"application\/ld+json\" class=\"yoast-schema-graph\">{\"@context\":\"https:\\\/\\\/schema.org\",\"@graph\":[{\"@type\":\"Article\",\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#article\",\"isPartOf\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/\"},\"author\":{\"name\":\"joapen\",\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\"},\"headline\":\"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX.\",\"datePublished\":\"2021-06-10T07:37:31+00:00\",\"dateModified\":\"2021-06-10T07:37:38+00:00\",\"mainEntityOfPage\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/\"},\"wordCount\":476,\"commentCount\":0,\"publisher\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\"},\"image\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/06\\\/image-2.png\",\"articleSection\":[\"Machine Learning\",\"Trading\"],\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"CommentAction\",\"name\":\"Comment\",\"target\":[\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#respond\"]}]},{\"@type\":\"WebPage\",\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/\",\"url\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/\",\"name\":\"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX. -\",\"isPartOf\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/#website\"},\"primaryImageOfPage\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#primaryimage\"},\"image\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#primaryimage\"},\"thumbnailUrl\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/06\\\/image-2.png\",\"datePublished\":\"2021-06-10T07:37:31+00:00\",\"dateModified\":\"2021-06-10T07:37:38+00:00\",\"description\":\"This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions - joapen projects\",\"breadcrumb\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#primaryimage\",\"url\":\"http:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/06\\\/image-2.png\",\"contentUrl\":\"http:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/06\\\/image-2.png\",\"width\":863,\"height\":279},{\"@type\":\"BreadcrumbList\",\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/2021\\\/06\\\/10\\\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\\\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"http:\\\/\\\/joapen.com\\\/blog\\\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX.\"}]},{\"@type\":\"WebSite\",\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/#website\",\"url\":\"http:\\\/\\\/joapen.com\\\/blog\\\/\",\"name\":\"joapen projects\",\"description\":\"Just a place to write\",\"publisher\":{\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\"},\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"http:\\\/\\\/joapen.com\\\/blog\\\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":[\"Person\",\"Organization\"],\"@id\":\"http:\\\/\\\/joapen.com\\\/blog\\\/#\\\/schema\\\/person\\\/23919df2312175fe9c4609203595b217\",\"name\":\"joapen\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\",\"url\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\",\"contentUrl\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\",\"width\":400,\"height\":400,\"caption\":\"joapen\"},\"logo\":{\"@id\":\"https:\\\/\\\/joapen.com\\\/blog\\\/wp-content\\\/uploads\\\/2021\\\/04\\\/joapen-mini.jpeg\"},\"sameAs\":[\"http:\\\/\\\/www.joapen.com\"]}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX. -","description":"This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions - joapen projects","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":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/","og_locale":"en_US","og_type":"article","og_title":"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX. -","og_description":"This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions - joapen projects","og_url":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/","og_site_name":"joapen projects","article_published_time":"2021-06-10T07:37:31+00:00","article_modified_time":"2021-06-10T07:37:38+00:00","og_image":[{"url":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png","type":"","width":"","height":""}],"author":"joapen","twitter_misc":{"Written by":"joapen","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#article","isPartOf":{"@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/"},"author":{"name":"joapen","@id":"http:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217"},"headline":"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX.","datePublished":"2021-06-10T07:37:31+00:00","dateModified":"2021-06-10T07:37:38+00:00","mainEntityOfPage":{"@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/"},"wordCount":476,"commentCount":0,"publisher":{"@id":"http:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217"},"image":{"@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#primaryimage"},"thumbnailUrl":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png","articleSection":["Machine Learning","Trading"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#respond"]}]},{"@type":"WebPage","@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/","url":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/","name":"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX. -","isPartOf":{"@id":"http:\/\/joapen.com\/blog\/#website"},"primaryImageOfPage":{"@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#primaryimage"},"image":{"@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#primaryimage"},"thumbnailUrl":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png","datePublished":"2021-06-10T07:37:31+00:00","dateModified":"2021-06-10T07:37:38+00:00","description":"This is the third version of a code I have started to write while learning the concepts of Machine Learning. Changes with respect the previous versions - joapen projects","breadcrumb":{"@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#primaryimage","url":"http:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png","contentUrl":"http:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png","width":863,"height":279},{"@type":"BreadcrumbList","@id":"http:\/\/joapen.com\/blog\/2021\/06\/10\/looking-for-a-machine-learning-model-that-hits-sp-500-daily-change-using-market-breadth-data-dix-gex-vix\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"http:\/\/joapen.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Looking for a machine learning model that hits S&P 500 daily change using market breadth data, DIX, GEX, VIX."}]},{"@type":"WebSite","@id":"http:\/\/joapen.com\/blog\/#website","url":"http:\/\/joapen.com\/blog\/","name":"joapen projects","description":"Just a place to write","publisher":{"@id":"http:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"http:\/\/joapen.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":["Person","Organization"],"@id":"http:\/\/joapen.com\/blog\/#\/schema\/person\/23919df2312175fe9c4609203595b217","name":"joapen","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg","url":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg","contentUrl":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg","width":400,"height":400,"caption":"joapen"},"logo":{"@id":"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/04\/joapen-mini.jpeg"},"sameAs":["http:\/\/www.joapen.com"]}]}},"_links":{"self":[{"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts\/5639","targetHints":{"allow":["GET"]}}],"collection":[{"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/comments?post=5639"}],"version-history":[{"count":1,"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts\/5639\/revisions"}],"predecessor-version":[{"id":5647,"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/posts\/5639\/revisions\/5647"}],"wp:attachment":[{"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/media?parent=5639"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/categories?post=5639"},{"taxonomy":"post_tag","embeddable":true,"href":"http:\/\/joapen.com\/blog\/wp-json\/wp\/v2\/tags?post=5639"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}
![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-2.png\")
<\/figure>\n\n\n\n![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-3.png\")
<\/figure>\n\n\n\n![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-4-1024x386.png\")
<\/figure>\n\n\n\n![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-5-1024x381.png\")
<\/figure>\n\n\n\n![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-6-1024x387.png\")
<\/figure>\n\n\n\n![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-7.png\")
<\/figure>\n\n\n\n![\"\"](\"https:\/\/joapen.com\/blog\/wp-content\/uploads\/2021\/06\/image-8.png\")
<\/figure>\n\n\n\n