{"id":92,"date":"2025-02-20T20:45:54","date_gmt":"2025-02-20T20:45:54","guid":{"rendered":"https:\/\/www.bgptrace.com\/blog\/?p=92"},"modified":"2025-02-21T09:57:45","modified_gmt":"2025-02-21T09:57:45","slug":"model-training-for-bitcoin-price-prediction-part-2","status":"publish","type":"post","link":"https:\/\/www.bgptrace.com\/blog\/?p=92","title":{"rendered":"Model Training on AMD 16-core CPU with 8GB RAM running in a virtual machine for Bitcoin Price Prediction &#8211; Part 2 &#8211; Updated"},"content":{"rendered":"\n<p>Continuing with Over 500,000+ Data Points for Bitcoin (BTC) Price Prediction<\/p>\n\n\n\n<p>Using the Python program, the first method I tried was <strong>SVR (Support Vector Regression)<\/strong> for prediction. However&#8230; <strong>how many steps should I use for prediction?<\/strong> \ud83e\udd14<\/p>\n\n\n\n<p>Previously, I used a <strong>Raspberry Pi 4B (4GB RAM)<\/strong> for prediction, and&#8230; <strong>OH&#8230;<\/strong> \ud83d\ude29<br>I don\u2019t even want to count the time again. Just imagine training a new model on a Raspberry Pi!<\/p>\n\n\n\n<p>So, I switched to an <strong>AMD 16-core CPU with 8GB RAM<\/strong> running in a virtual machine to perform the prediction.<\/p>\n\n\n\n<ul class=\"wp-block-list\">\n<li><strong>60 steps calculation:<\/strong> Took <strong>7 hours<\/strong> \ud83d\ude35<\/li>\n\n\n\n<li><strong>120 steps:<\/strong> &#8230;Man&#8230; still running after <strong>20 hours<\/strong>! \ud83d\ude2b  Finally !!! 33 Hours<\/li>\n<\/ul>\n\n\n\n<p>Do I need an <strong>M4 machine<\/strong> for this? \ud83d\udcbb\u26a1<\/p>\n\n\n\n<p>ChatGPT provided another approach.<br><strong>OK, let\u2019s test it&#8230; I\u2019ll let you know how it goes!<\/strong> \ud83d\ude80<br><br>\ud83e\uddea <strong>Quick Example of More Time Steps Effect<\/strong><\/p>\n\n\n\n<figure class=\"wp-block-table\"><table class=\"has-fixed-layout\"><thead><tr><th>Time Step (X Length)<\/th><th>Predicted Accuracy<\/th><th>Notes<\/th><\/tr><\/thead><tbody><tr><td>30<\/td><td>\u2b50\u2b50\u2b50<\/td><td>Quick but less accurate for long-term trends.<\/td><\/tr><tr><td>60<\/td><td>\u2b50\u2b50\u2b50\u2b50<\/td><td>Balanced context and performance.<\/td><\/tr><tr><td>120<\/td><td>\u2b50\u2b50\u2b50\u2b50\u00bd<\/td><td>Better for long-term trends but slower.<\/td><\/tr><tr><td>240<\/td><td>\u2b50\u2b50<\/td><td>Risk of overfitting and slower training.<\/td><\/tr><\/tbody><\/table><\/figure>\n\n\n\n<p>#SVR #Prediction #Computing #AI #Step #ChatGPT #Python #Bitcoin #crypto #Cryptocurrency #trading #price #virtualmachine #vm #raspberrypi #ram #CPU #CUDB #AMD #Nvidia<\/p>\n","protected":false},"excerpt":{"rendered":"<p>Continuing with Over 500,000+ Data Points for Bitcoin (BTC) Price Prediction Using the Python program, the first method I tried was SVR (Support Vector Regression) for prediction. However&#8230; how many steps should I use for prediction? \ud83e\udd14 Previously, I used a Raspberry Pi 4B (4GB RAM) for prediction, and&#8230; OH&#8230; \ud83d\ude29I don\u2019t even want to &hellip; <a href=\"https:\/\/www.bgptrace.com\/blog\/?p=92\" class=\"more-link\">Continue reading<span class=\"screen-reader-text\"> &#8220;Model Training on AMD 16-core CPU with 8GB RAM running in a virtual machine for Bitcoin Price Prediction &#8211; Part 2 &#8211; Updated&#8221;<\/span><\/a><\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[3],"tags":[36,49,92,39,102,96,104,56,50,101,106,35,44,42,103,100,105,107,48],"class_list":["post-92","post","type-post","status-publish","format-standard","hentry","category-ai","tag-ai","tag-amd","tag-bitcoin","tag-chatgpt","tag-computing","tag-crypto","tag-cryptocurrency","tag-cudb","tag-nvidia","tag-predition","tag-price","tag-python","tag-ram","tag-raspberrypi","tag-step","tag-svr","tag-trading","tag-virtualmachine","tag-vm"],"_links":{"self":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/92","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=92"}],"version-history":[{"count":4,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/92\/revisions"}],"predecessor-version":[{"id":97,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=\/wp\/v2\/posts\/92\/revisions\/97"}],"wp:attachment":[{"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=92"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=92"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.bgptrace.com\/blog\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=92"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}