{"id":31395,"date":"2018-02-28T21:32:22","date_gmt":"2018-02-28T18:32:22","guid":{"rendered":"https:\/\/www.altoros.com\/blog\/?p=31395"},"modified":"2019-08-14T16:36:58","modified_gmt":"2019-08-14T13:36:58","slug":"automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs","status":"publish","type":"post","link":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/","title":{"rendered":"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs"},"content":{"rendered":"<div id=\"ez-toc-container\" class=\"ez-toc-v2_0_79_2 counter-hierarchy ez-toc-counter ez-toc-transparent ez-toc-container-direction\">\n<div class=\"ez-toc-title-container\">\n<p class=\"ez-toc-title\" style=\"cursor:inherit\">Table of Contents<\/p>\n<span class=\"ez-toc-title-toggle\"><a href=\"#\" class=\"ez-toc-pull-right ez-toc-btn ez-toc-btn-xs ez-toc-btn-default ez-toc-toggle\" aria-label=\"Toggle Table of Content\"><span class=\"ez-toc-js-icon-con\"><span class=\"\"><span class=\"eztoc-hide\" style=\"display:none;\">Toggle<\/span><span class=\"ez-toc-icon-toggle-span\"><svg style=\"fill: #999;color:#999\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" class=\"list-377408\" width=\"20px\" height=\"20px\" viewBox=\"0 0 24 24\" fill=\"none\"><path d=\"M6 6H4v2h2V6zm14 0H8v2h12V6zM4 11h2v2H4v-2zm16 0H8v2h12v-2zM4 16h2v2H4v-2zm16 0H8v2h12v-2z\" fill=\"currentColor\"><\/path><\/svg><svg style=\"fill: #999;color:#999\" class=\"arrow-unsorted-368013\" xmlns=\"http:\/\/www.w3.org\/2000\/svg\" width=\"10px\" height=\"10px\" viewBox=\"0 0 24 24\" version=\"1.2\" baseProfile=\"tiny\"><path d=\"M18.2 9.3l-6.2-6.3-6.2 6.3c-.2.2-.3.4-.3.7s.1.5.3.7c.2.2.4.3.7.3h11c.3 0 .5-.1.7-.3.2-.2.3-.5.3-.7s-.1-.5-.3-.7zM5.8 14.7l6.2 6.3 6.2-6.3c.2-.2.3-.5.3-.7s-.1-.5-.3-.7c-.2-.2-.4-.3-.7-.3h-11c-.3 0-.5.1-.7.3-.2.2-.3.5-.3.7s.1.5.3.7z\"\/><\/svg><\/span><\/span><\/span><\/a><\/span><\/div>\n<nav><ul class='ez-toc-list ez-toc-list-level-1 ' ><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-1\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#Burdens_of_damage_estimation_in_auto_insurance\" >Burdens of damage estimation in auto insurance<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-2\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#Enabling_multi-instance_learning\" >Enabling multi-instance learning<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-3\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#Overcoming_the_hurdles\" >Overcoming the hurdles<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-4\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#Want_details_Watch_the_video\" >Want details? Watch the video!<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-5\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#Related_slides\" >Related slides<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-6\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#Further_reading\" >Further reading<\/a><\/li><li class='ez-toc-page-1 ez-toc-heading-level-3'><a class=\"ez-toc-link ez-toc-heading-7\" href=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#About_the_experts\" >About the experts<\/a><\/li><\/ul><\/nav><\/div>\n<h3><span class=\"ez-toc-section\" id=\"Burdens_of_damage_estimation_in_auto_insurance\"><\/span>Burdens of damage estimation in auto insurance<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>At <a href=\"https:\/\/www.meetup.com\/ru-RU\/TensorFlow-London\/events\/246867281\/\" rel=\"noopener noreferrer\" target=\"_blank\">TensorFlow meetup<\/a> in London, <a href=\"https:\/\/www.linkedin.com\/in\/marcel-horstmann-43a0b062\/\" rel=\"noopener noreferrer\" target=\"_blank\">Marcel Horstmann<\/a> and <a href=\"https:\/\/www.linkedin.com\/in\/laurentdecamp\/\" rel=\"noopener noreferrer\" target=\"_blank\">Laurent Decamp<\/a> of Tractable shared their experience in building a working solution for automotive insurance that will allow for improving the process of damage estimation.<\/p>\n<p>When a vehicle gets damaged in an accident, an insurer has to cover the repair cost. However, the estimation for it is done by a body shop, which may overcharge sometimes. Furthermore, the estimation process is manual and requires human experts and their time to evaluate the damage.<\/p>\n<p>Employing machine learning, it&#8217;s possible to train a model that will recognize the damaged car parts, assess damage, <a href=\"https:\/\/www.altoros.com\/blog\/tensorflow-in-finance-discussing-predictive-analytics-and-budget-planning\/\">make predictions<\/a> about what kind of repair is needed, and estimate how much it may cost.<\/p>\n<p>To deliver accurate estimation, the model should be capable of predicting what type of maintenance exactly is to follow. As it influences the final cost, it is necessary for the model to distinguish, for instance, whether the damaged car part can be still fixed or has to be replaced.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-31420\" \/><\/a><small>Image credit: Tractable<\/small><\/center><\/p>\n<p><em>Visual models<\/em>, as Marcel calls them, are responsible for <a href=\"https:\/\/www.altoros.com\/blog\/image-and-text-recognition-with-tensorflow-using-convolutional-neural-networks\/\">image recognition<\/a> and damage assessment. Repair estimate belongs to the domain of <em>metadata models<\/em>, while prediction uses both the models.<\/p>\n<blockquote><p><em>&#8220;So, we have to decide if this part is so damaged that we need a new one, and then we have to figure out what the part number is, and how expensive it is.&#8221;<br \/>\n\u2014Marcel Horstmann, Tractable<\/em><\/p><\/blockquote>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Enabling_multi-instance_learning\"><\/span>Enabling multi-instance learning<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>To build a model capable of estimating repair cost, there is a need for data to train this model on. Partnering with auto insurers, Marcel and Laurent got access to an immerse collection of 130+ million images of damaged cars. Furthermore, these images have annotations\u2014highlighting which vehicle part was particularly damaged.<\/p>\n<p><p>Within a single insurance claim, Marcel and Laurent usually exploit between 15\u201350 images to train the model. Some of them depict the overall vehicle condition, some illustrate the damage occurred, and some are just irrelevant for the assessment case.<\/p>\n<p>To make it all work, they rely on the following technology stack:<\/p>\n<ul>\n<li>Amazon S3 to store data<\/li>\n<li>A custom-built API to download, decompress, and buffer images in parallel<\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/building-a-keras-based-image-classifier-using-tensorflow-for-a-back-end\/\">Keras<\/a> and TensorFlow to actually train the model<\/li>\n<\/ul>\n<p>Marcel referred to <em>multi-instance learning<\/em> that they were trying to enable. By this, he meant that the model is to check a variety of images\u2014taken from different angles\u2014of the same damaged vehicle before making a final prediction. For the purpose, the team also employed the <a href=\"https:\/\/arxiv.org\/abs\/1512.03385v1\" rel=\"noopener noreferrer\" target=\"_blank\">ResNet<\/a> convolutional neural network and tested a bunch of approaches to pooling.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-training-a-model.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-training-a-model.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-31421\" \/><\/a><small>Image credit: Tractable<\/small><\/center><\/p>\n<p>On the way, there were some challenges to address:<\/p>\n<ul>\n<li style=\"margin-bottom: 6px\">Providing real-time inference<\/li>\n<li style=\"margin-bottom: 6px\">Using a relatively modest volume of data (1.2 million images submitted by an individual insurer daily, which can be treated as 12.5 images\/second throughput per model)<\/li>\n<li>Ensuring an ability to sustain irregular peaks of traffic<\/li>\n<\/ul>\n<p>Additional constraints were imposed through training 12 data sets\u2014containing images of 12 car parts\u2014as different models. In addition, the recognition stage and assessment stage required separate treating, so it resulted in 24 models to train.<\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Overcoming_the_hurdles\"><\/span>Overcoming the hurdles<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p>The team decided to deploy each model on a dedicated GPU. This allowed for using large batch size and achieving high throughput (170 images\/second per model). However, the cost it took mounted $16,000 per months for 24 models, which Laurent naturally coined as expensive and resource-wasteful.<\/p>\n<p>Looking for better options, the team considered using CPU for inference or collocating multiple models on the same GPU. The first option proved invalid due to scalability issues. Running parallel processes on the same GPU improved the situation a bit, still one needs to reserve additional memory for TensorFlow and Keras apart from the model itself and a batch.<\/p>\n<p>Betting on the latter strategy, engineers were able to put either five models with a batch size of 32 or six models with a batch size of 16 on the same GPU. It resulted in a satisfying throughput, though they had to compromise performance to a certain extent.<\/p>\n<p><center><a href=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-training-a-model-on-gpu.png\"><img decoding=\"async\" src=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-training-a-model-on-gpu.png\" alt=\"\" width=\"640\" class=\"aligncenter size-full wp-image-31422\" \/><\/a><small>Image credit: Tractable<\/small><\/center><\/p>\n<p>There is a potential to boost the performance by optimizing the process of image decompression. According to Laurent, it may happen if they take a single Python process, warm up models weights, and then sequentially run the models. This way, he estimates it will be possible to scale up to 80\u201385 models on a GPU.<\/p>\n<p><p>In the long run, the team utilized four GPUs to train 24 models. The total cost for the computing resources amounted for $3,300 with around $12,700 saved monthly\u2014in comparison to the initial setup.<\/p>\n<p>As a result of this research, Tractable has developed two products <a href=\"https:\/\/tractable.ai\/products\/vehicle-damage\/#ai-review\" rel=\"noopener noreferrer\" target=\"_blank\">AI Review<\/a> and <a href=\"https:\/\/tractable.ai\/products\/vehicle-damage\/#ai-fnol-triage\" rel=\"noopener noreferrer\" target=\"_blank\">AI FNOL Triage<\/a>. You can also read <a href=\"https:\/\/www.repairerdrivennews.com\/2017\/10\/09\/tractable-data-cleanup-volume-rules-solve-gigo-problem-of-using-past-claims-for-ai-photo-estimating\/\" rel=\"noopener noreferrer\" target=\"_blank\">this article<\/a>, featuring a demo of the company&#8217;s solutions.<\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Want_details_Watch_the_video\"><\/span>Want details? Watch the video!<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><center><iframe loading=\"lazy\" width=\"560\" height=\"315\" src=\"https:\/\/www.youtube.com\/embed\/K_avU3CBF6w\" frameborder=\"0\" allow=\"autoplay; encrypted-media\" allowfullscreen><\/iframe><\/center><\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Related_slides\"><\/span>Related slides<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><center><iframe loading=\"lazy\" src=\"https:\/\/www.slideshare.net\/slideshow\/embed_code\/key\/dF5EyZKdp4T1kj\" width=\"427\" height=\"356\" frameborder=\"0\" marginwidth=\"0\" marginheight=\"0\" scrolling=\"no\" style=\"border:1px solid #CCC; border-width:1px; margin-bottom:5px; max-width: 100%;\" allowfullscreen> <\/iframe><\/center><\/p>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"Further_reading\"><\/span>Further reading<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<ul>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/automotive-blockchain-from-manufacturing-to-security-to-insurance\/\">Automotive Blockchain: from Manufacturing to Security to Insurance<\/a><\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/how-tensorflow-can-detect-and-predict-wildfires\/\"><a href=\"https:\/\/www.altoros.com\/blog\/blockchain-for-insurance-reduced-fraud-and-streamlined-claims\/\" rel=\"noopener noreferrer\" target=\"_blank\">Blockchain for Insurance: Less Fraud, Faster Claims, and New Models<\/a><\/a><\/li>\n<li><a href=\"https:\/\/www.altoros.com\/blog\/using-machine-learning-and-tensorflow-to-recognize-traffic-signs\/\">Using Machine Learning and TensorFlow to Recognize Traffic Signs<\/a><\/li>\n<\/ul>\n<p>&nbsp;<\/p>\n<h3><span class=\"ez-toc-section\" id=\"About_the_experts\"><\/span>About the experts<span class=\"ez-toc-section-end\"><\/span><\/h3>\n<p><small><a href=\"https:\/\/www.linkedin.com\/in\/marcel-horstmann-43a0b062\/\" rel=\"noopener noreferrer\" target=\"_blank\">Marcel Horstmann<\/a> is Deep Learning Researcher at Tractable with a background in quantum optics. With an MS degree in Physics, he is experienced in applying deep learning to both solar power prediction and energy efficiency.<\/small><\/p>\n<p><small><a href=\"https:\/\/www.linkedin.com\/in\/laurentdecamp\/\" rel=\"noopener noreferrer\" target=\"_blank\">Laurent Decamp<\/a> is Deep Learning Engineer at Tractable. Recently, he was engaged in a research project on real-time image-based localization in large-scale outdoor environments. Laurent has got MS in Artificial Intelligence from the University of Edinburgh.<\/small><\/p>\n","protected":false},"excerpt":{"rendered":"<p>Burdens of damage estimation in auto insurance<\/p>\n<p>At TensorFlow meetup in London, Marcel Horstmann and Laurent Decamp of Tractable shared their experience in building a working solution for automotive insurance that will allow for improving the process of damage estimation.<\/p>\n<p>When a vehicle gets damaged in an accident, an insurer has to [&#8230;]<\/p>\n","protected":false},"author":3,"featured_media":33261,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_acf_changed":false,"content-type":"","footnotes":"","_links_to":"","_links_to_target":""},"categories":[7],"tags":[883,927,748,749],"class_list":["post-31395","post","type-post","status-publish","format-standard","has-post-thumbnail","hentry","category-news-and-opinion","tag-automotive","tag-insurance","tag-machine-learning","tag-tensorflow"],"acf":[],"yoast_head":"<!-- This site is optimized with the Yoast SEO plugin v26.6 - https:\/\/yoast.com\/wordpress\/plugins\/seo\/ -->\n<title>Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs | Altoros<\/title>\n<meta name=\"description\" content=\"Learn how AI tools, such as TensorFlow and Keras, can help insurers to automate damage assessment and avoid overcharging by a car parts supplier.\" \/>\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.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs | Altoros\" \/>\n<meta property=\"og:description\" content=\"Burdens of damage estimation in auto insurance At TensorFlow meetup in London, Marcel Horstmann and Laurent Decamp of Tractable shared their experience in building a working solution for automotive insurance that will allow for improving the process of damage estimation. When a vehicle gets damaged in an accident, an insurer has to [...]\" \/>\n<meta property=\"og:url\" content=\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/\" \/>\n<meta property=\"og:site_name\" content=\"Altoros\" \/>\n<meta property=\"article:published_time\" content=\"2018-02-28T18:32:22+00:00\" \/>\n<meta property=\"article:modified_time\" content=\"2019-08-14T13:36:58+00:00\" \/>\n<meta property=\"og:image\" content=\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif\" \/>\n\t<meta property=\"og:image:width\" content=\"640\" \/>\n\t<meta property=\"og:image:height\" content=\"480\" \/>\n\t<meta property=\"og:image:type\" content=\"image\/gif\" \/>\n<meta name=\"author\" content=\"Sophia Turol\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"Sophia Turol\" \/>\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\":\"WebPage\",\"@id\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/\",\"url\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/\",\"name\":\"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs | Altoros\",\"isPartOf\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/#website\"},\"primaryImageOfPage\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#primaryimage\"},\"image\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#primaryimage\"},\"thumbnailUrl\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif\",\"datePublished\":\"2018-02-28T18:32:22+00:00\",\"dateModified\":\"2019-08-14T13:36:58+00:00\",\"author\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/58194952af19fe7b2b830846e077a58e\"},\"breadcrumb\":{\"@id\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#breadcrumb\"},\"inLanguage\":\"en-US\",\"potentialAction\":[{\"@type\":\"ReadAction\",\"target\":[\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/\"]}]},{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#primaryimage\",\"url\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif\",\"contentUrl\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif\",\"width\":640,\"height\":480},{\"@type\":\"BreadcrumbList\",\"@id\":\"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#breadcrumb\",\"itemListElement\":[{\"@type\":\"ListItem\",\"position\":1,\"name\":\"Home\",\"item\":\"https:\/\/www.altoros.com\/blog\/\"},{\"@type\":\"ListItem\",\"position\":2,\"name\":\"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs\"}]},{\"@type\":\"WebSite\",\"@id\":\"https:\/\/www.altoros.com\/blog\/#website\",\"url\":\"https:\/\/www.altoros.com\/blog\/\",\"name\":\"Altoros\",\"description\":\"Insight\",\"potentialAction\":[{\"@type\":\"SearchAction\",\"target\":{\"@type\":\"EntryPoint\",\"urlTemplate\":\"https:\/\/www.altoros.com\/blog\/?s={search_term_string}\"},\"query-input\":{\"@type\":\"PropertyValueSpecification\",\"valueRequired\":true,\"valueName\":\"search_term_string\"}}],\"inLanguage\":\"en-US\"},{\"@type\":\"Person\",\"@id\":\"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/58194952af19fe7b2b830846e077a58e\",\"name\":\"Sophia Turol\",\"image\":{\"@type\":\"ImageObject\",\"inLanguage\":\"en-US\",\"@id\":\"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/image\/\",\"url\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2019\/05\/trello_card-96x96.jpg\",\"contentUrl\":\"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2019\/05\/trello_card-96x96.jpg\",\"caption\":\"Sophia Turol\"},\"description\":\"Sophia Turol is passionate about delivering well-structured articles that cater for picky technical audience. With 3+ years in technical writing and 5+ years in editorship, she enjoys collaboration with developers to create insightful, yet intelligible technical tutorials, overviews, and case studies. Sophie is enthusiastic about deep learning solutions\u2014TensorFlow in particular\u2014and PaaS systems, such as Cloud Foundry.\",\"url\":\"https:\/\/www.altoros.com\/blog\/author\/sophie-turol\/\"}]}<\/script>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs | Altoros","description":"Learn how AI tools, such as TensorFlow and Keras, can help insurers to automate damage assessment and avoid overcharging by a car parts supplier.","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.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/","og_locale":"en_US","og_type":"article","og_title":"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs | Altoros","og_description":"Burdens of damage estimation in auto insurance At TensorFlow meetup in London, Marcel Horstmann and Laurent Decamp of Tractable shared their experience in building a working solution for automotive insurance that will allow for improving the process of damage estimation. When a vehicle gets damaged in an accident, an insurer has to [...]","og_url":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/","og_site_name":"Altoros","article_published_time":"2018-02-28T18:32:22+00:00","article_modified_time":"2019-08-14T13:36:58+00:00","og_image":[{"width":640,"height":480,"url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif","type":"image\/gif"}],"author":"Sophia Turol","twitter_misc":{"Written by":"Sophia Turol","Est. reading time":"4 minutes"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"WebPage","@id":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/","url":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/","name":"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs | Altoros","isPartOf":{"@id":"https:\/\/www.altoros.com\/blog\/#website"},"primaryImageOfPage":{"@id":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#primaryimage"},"image":{"@id":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#primaryimage"},"thumbnailUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif","datePublished":"2018-02-28T18:32:22+00:00","dateModified":"2019-08-14T13:36:58+00:00","author":{"@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/58194952af19fe7b2b830846e077a58e"},"breadcrumb":{"@id":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/"]}]},{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#primaryimage","url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif","contentUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2018\/02\/tensorflow-keras-for-automotive-insurance-featured-v1-1.gif","width":640,"height":480},{"@type":"BreadcrumbList","@id":"https:\/\/www.altoros.com\/blog\/automotive-insurance-with-tensorflow-estimating-damage-and-repair-costs\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Home","item":"https:\/\/www.altoros.com\/blog\/"},{"@type":"ListItem","position":2,"name":"Automotive Insurance with TensorFlow: Estimating Damage \/ Repair Costs"}]},{"@type":"WebSite","@id":"https:\/\/www.altoros.com\/blog\/#website","url":"https:\/\/www.altoros.com\/blog\/","name":"Altoros","description":"Insight","potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/www.altoros.com\/blog\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Person","@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/58194952af19fe7b2b830846e077a58e","name":"Sophia Turol","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/www.altoros.com\/blog\/#\/schema\/person\/image\/","url":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2019\/05\/trello_card-96x96.jpg","contentUrl":"https:\/\/www.altoros.com\/blog\/wp-content\/uploads\/2019\/05\/trello_card-96x96.jpg","caption":"Sophia Turol"},"description":"Sophia Turol is passionate about delivering well-structured articles that cater for picky technical audience. With 3+ years in technical writing and 5+ years in editorship, she enjoys collaboration with developers to create insightful, yet intelligible technical tutorials, overviews, and case studies. Sophie is enthusiastic about deep learning solutions\u2014TensorFlow in particular\u2014and PaaS systems, such as Cloud Foundry.","url":"https:\/\/www.altoros.com\/blog\/author\/sophie-turol\/"}]}},"_links":{"self":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/31395","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/comments?post=31395"}],"version-history":[{"count":33,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/31395\/revisions"}],"predecessor-version":[{"id":46016,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/posts\/31395\/revisions\/46016"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/media\/33261"}],"wp:attachment":[{"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/media?parent=31395"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/categories?post=31395"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.altoros.com\/blog\/wp-json\/wp\/v2\/tags?post=31395"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}