{"id":2294,"date":"2025-05-29T08:59:18","date_gmt":"2025-05-29T08:59:18","guid":{"rendered":"https:\/\/artelnics.com\/?post_type=case_researchs&#038;p=2294"},"modified":"2026-06-30T14:08:30","modified_gmt":"2026-06-30T14:08:30","slug":"horizon-2020","status":"publish","type":"case_researchs","link":"https:\/\/artelnics.com\/case_researchs\/horizon-2020\/","title":{"rendered":"Horizon 2020 &#8211; A high-performance solution for predictive analytics (Neural Designer)"},"content":{"rendered":"<style id=\"atl-opennn-style\">@import url('https:\/\/fonts.googleapis.com\/css2?family=Roboto:wght@400;500;700;800;900&display=swap');\/* codex-artelnics-opennn-visual-sync-v5 *\/:root{--opennn-navy:#1E5374;--opennn-blue:#1E5374;--opennn-sky:#56A1C8;--opennn-sky-light:#B6D7E7;--opennn-wash:#EAF3F9;--opennn-ink:#212121;--opennn-text:#212121;--opennn-muted:#5F6368;--opennn-line:#D7E4EA;--opennn-soft:#F5F9FC;--opennn-white:#FFFFFF;--artelnics-blue:var(--opennn-blue);--artelnics-cyan:var(--opennn-sky);--artelnics-deep:var(--opennn-navy);--artelnics-navy:var(--opennn-navy);--artelnics-bg:var(--opennn-soft);--artelnics-text:var(--opennn-text);--artelnics-muted:var(--opennn-muted);--artelnics-line:var(--opennn-line);--artelnics-soft:var(--opennn-soft);--artelnics-white:var(--opennn-white);--content-width:1180px;}:root{--artelnics-blue:#56A1C8;--artelnics-cyan:#56A1C8;--artelnics-deep:#1E5374;--home-blue:#56A1C8;--home-sky:#56A1C8;--home-light:#56A1C8;--home-navy:#1E5374;}body{font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif;}h1,h2,h3,h4,h5,.atl-eyebrow,.eyebrow,.button,.button-primary,.site-menu,.brand{font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif;}.site-header{background:rgba(26,74,102,.96);}.site-menu a:hover{color:#56A1C8;}.site-menu .menu-contact a{background:#56A1C8;}.site-menu .menu-contact a:hover{background:#56A1C8;}.atl-hero,.single-hero,.page-hero,.atl-home-hero{background:#1E5374;}.atl-eyebrow,.single-hero .eyebrow,.page-hero .eyebrow{color:#B6D7E7;font-weight:600;}.atl-card{border:1px solid #B6D7E7;border-radius:10px;box-shadow:0 16px 42px rgba(30,83,116,.08);}\/* codex-artelnics-opennn-visual-sync-v5-overrides-start *\/html,body,#page,.site,.site-main,#content,.entry-content{background:#F5F9FC!important}body,.atl-home,.atl-section,.atl-content-section,.atl-case{font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;color:#212121!important;font-size:17px;line-height:1.65}.site-header{background:rgba(26,74,102,.96)!important;border-bottom:1px solid rgba(255,255,255,.1)!important;box-shadow:0 10px 30px rgba(6,27,52,.18)!important}.site-menu a{color:#FFFFFF!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-size:16px!important;font-weight:800!important}.site-menu a:hover{color:#56A1C8!important}.site-menu .menu-contact a,.site-menu .menu-github a{background:#56A1C8!important;color:#FFFFFF!important;border-radius:8px!important}.site-footer{background:#1E5374!important;color:rgba(255,255,255,.84)!important}h1,h2,h3,h4,h5,h6,.atl-eyebrow,.eyebrow,.button,.atl-home-button,.site-menu,.brand{font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;letter-spacing:0!important}.atl-home-hero,.atl-hero,section.atl-hero{background:radial-gradient(circle at 78% 20%,rgba(86,161,200,.22),transparent 24%),linear-gradient(135deg,#1E5374 0%,#1E5374 60%,#1E5374 100%)!important;color:#FFFFFF!important}.atl-home-eyebrow,.atl-eyebrow,section.atl-hero .atl-eyebrow{color:#B6D7E7!important;font-size:14px!important;font-weight:600!important;letter-spacing:.08em!important}.atl-home-hero h1,.atl-hero h1,body section.atl-hero .atl-hero-inner>h1,body .entry-content section.atl-hero h1{color:#FFFFFF!important;-webkit-text-fill-color:#FFFFFF!important;opacity:1!important;font-size:54px!important;font-weight:700!important;line-height:1.08!important}.atl-home-lead,.atl-hero p,body section.atl-hero p:not(.atl-eyebrow){color:#EAF3F9!important;-webkit-text-fill-color:#EAF3F9!important;font-size:18px!important;line-height:1.7!important}.atl-home-section,.atl-section,.atl-home-cta,.atl-home-section-soft,.atl-home-section-dark,.atl-section-soft{background:#F5F9FC!important;color:#212121!important}.atl-home-section-head h2,.atl-section-header h2,.atl-home-cta-box h2,.atl-content-section h1{color:#212121!important;font-size:36px!important;font-weight:700!important;line-height:1.15!important}.atl-home-section-head p,.atl-section-header p,.atl-home-cta-box p,.atl-content-section p{color:#5F6368!important;font-size:17px!important;line-height:1.7!important}.atl-card,.atl-home-service,.atl-home-product,.atl-home-case,.atl-home-industry,.atl-home-programme{background:#F5F9FC!important;color:#212121!important;box-shadow:-12px -12px 24px rgba(255,255,255,.96),12px 12px 24px rgba(30,83,116,.13)!important}.atl-card h3,.atl-home-service h3,.atl-home-product h3,.atl-home-case h3,.atl-home-programme h3{color:#212121!important;font-size:22px!important;font-weight:800!important;line-height:1.15!important}.atl-card p,.atl-home-service p,.atl-home-product p,.atl-home-case p,.atl-home-programme p{color:#5F6368!important;font-size:17px!important;line-height:1.58!important}.atl-card a,.atl-home-product a,.atl-home-case a,.text-link{color:#56A1C8!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-weight:700!important}.atl-home-button,.button,.button-primary,.button-secondary,body a.button,body a.button-primary,body a.button-secondary{background:#56A1C8!important;color:#FFFFFF!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-size:17px!important;font-weight:800!important;border-radius:10px!important}.atl-home-button:hover,.button:hover,.button-primary:hover,.button-secondary:hover{background:#56A1C8!important;color:#FFFFFF!important}.atl-home-service .atl-service-icon{color:#56A1C8!important}.atl-case{color:#212121!important;max-width:980px}.atl-case h2{color:#3B86AD!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-size:34px!important;font-weight:700!important;line-height:1.18!important}.atl-case h3,.atl-case .card strong{color:#212121!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important}.atl-case p,.atl-case li{color:#212121!important;font-size:19px!important;line-height:1.62!important}.atl-case .lead{color:#5F6368!important;font-size:20px!important;line-height:1.5!important}.atl-case .tag{background:#EAF3F9!important;color:#1E5374!important;border-color:#D7E4EA!important}.atl-case .card{background:#FFFFFF!important;border-color:#D7E4EA!important;border-radius:8px!important}.atl-case figcaption{color:#5F6368!important}@media(max-width:767px){.atl-home-hero h1,.atl-hero h1,body section.atl-hero .atl-hero-inner>h1{font-size:38px!important}.atl-home-section-head h2,.atl-section-header h2,.atl-home-cta-box h2,.atl-content-section h1{font-size:28px!important}.atl-case h2{font-size:28px!important}.atl-case p,.atl-case li{font-size:17px!important}.atl-home-lead,.atl-hero p,body section.atl-hero p:not(.atl-eyebrow){font-size:17px!important}}.cky-consent-container{left:auto!important;right:40px!important;bottom:40px!important;max-width:440px!important;width:min(440px,calc(100vw - 32px))!important;z-index:99999999!important}.cky-consent-container .cky-consent-bar{background:#FFFFFF!important;border:1px solid #D7E4EA!important;border-radius:8px!important;box-shadow:0 18px 42px rgba(30,83,116,.16)!important;color:#212121!important;padding:24px 26px!important}.cky-title,.cky-notice .cky-title{color:#212121!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-size:18px!important;font-weight:800!important;line-height:1.25!important}.cky-notice-des,.cky-notice-des *{color:#5F6368!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-size:14px!important;line-height:1.55!important}.cky-notice-group{display:block!important}.cky-notice-btn-wrapper{display:flex!important;flex-wrap:nowrap!important;gap:10px!important;justify-content:space-between!important;margin-top:18px!important}.cky-btn{flex:1 1 0!important;min-width:0!important;width:auto!important;min-height:44px!important;padding:0 20px!important;border-radius:0!important;font-family:\"Roboto\",\"Segoe UI\",Arial,sans-serif!important;font-size:14px!important;font-weight:700!important}.cky-btn-accept{background:#1E5374!important;border-color:#1E5374!important;color:#FFFFFF!important}.cky-btn-reject,.cky-btn-customize{background:#FFFFFF!important;border:1px solid #1E5374!important;color:#1E5374!important}.cky-btn:hover{opacity:1!important;box-shadow:none!important}@media(max-width:767px){.cky-consent-container{left:16px!important;right:16px!important;bottom:16px!important;width:auto!important;max-width:none!important}.cky-notice-btn-wrapper{flex-direction:column!important}.cky-btn{width:100%!important}}\/* codex-artelnics-opennn-visual-sync-v5-overrides-end *\/<\/style>\n<p><a href=\"\/case_researchs\">\u2039 Back to Case Research<\/a><\/p>\n<h3><strong>Context and General Objectives\u00a0<\/strong><\/h3>\n<p>The digital age demands tools for intelligent data analysis. Artelnics developed Neural Designer, a deep learning solution for predictive analytics, to help organizations make better decisions from their vast data. It&#8217;s successfully applied in engineering, marketing, and health.\u00a0<\/p>\n<p>The project&#8217;s main goal was to integrate an innovative model selection framework into Neural Designer to handle complex datasets, requiring support for big data and super-computing clusters. Work Performed and Key Results During Phase 1 of the SME Instrument, Artelnics made substantial progress across the technical, commercial, legal, and financial dimensions of Neural Designer.\u00a0<\/p>\n<p>On the technical front, the development team has expanded, and a new, more optimized version of Neural Designer, packed with innovations, has been released. Crucially, various model selection algorithms have been developed to automatically identify the most relevant variables within a dataset.\u00a0<\/p>\n<h3><strong>Advances Beyond State-of-the-Art and Expected Impact\u00a0<\/strong><\/h3>\n<p>Many applications of predictive analytics, ranging from customer segmentation to medical diagnosis, stem from complex interactions among diverse variables. A software tool that can efficiently untangle these factors represents a significant innovation with the potential to disrupt the existing predictive analytics market. Neural Designer is poised to overcome these challenges, guaranteeing optimal results by offering innovative model selection techniques coupled with high computational performance. The immediate benefit for customers is a strengthening of their businesses, enhancing their competitiveness.\u00a0<\/p>\n<p>The potential societal impact of applying predictive analytics is vast; in engineering, it can lead to reduced gas emissions or minimized equipment faults; in business, it aligns products with customers and improves the buying experience; and in health, data mining can contribute to better diagnoses and more effective treatments.\u00a0<\/p>\n<p>Neural Designer achieves this by seamlessly integrating the best techniques from artificial intelligence and computer engineering to construct the most powerful predictive models from large-scale datasets, thereby enabling the development of truly impactful predictive analytics applications.<\/p>\n<p><img loading=\"lazy\" decoding=\"async\" src=\"https:\/\/artelnics.com\/wp-content\/uploads\/2023\/08\/neuraldesigner_web.webp\" alt=\"Neural Designer website\" width=\"406\" height=\"257\" \/><\/p>\n<p>[elementor-template id=&#8221;764&#8243;]<\/p>\n","protected":false},"excerpt":{"rendered":"<p>\u2039 Back to Case Research Context and General Objectives\u00a0 The digital age demands tools for intelligent data analysis. Artelnics developed Neural Designer, a deep learning solution for predictive analytics, to help organizations make better decisions from their vast data. It&#8217;s successfully applied in engineering, marketing, and health.\u00a0 The project&#8217;s main goal was to integrate an [&hellip;]<\/p>\n","protected":false},"featured_media":2295,"parent":0,"menu_order":0,"template":"elementor_header_footer","categories":[],"tags":[],"class_list":["post-2294","case_researchs","type-case_researchs","status-publish","has-post-thumbnail","hentry"],"acf":[],"_links":{"self":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_researchs\/2294","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_researchs"}],"about":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/types\/case_researchs"}],"version-history":[{"count":53,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_researchs\/2294\/revisions"}],"predecessor-version":[{"id":3056,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/case_researchs\/2294\/revisions\/3056"}],"wp:featuredmedia":[{"embeddable":true,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/media\/2295"}],"wp:attachment":[{"href":"https:\/\/artelnics.com\/api\/wp\/v2\/media?parent=2294"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/categories?post=2294"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/artelnics.com\/api\/wp\/v2\/tags?post=2294"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}