Breaking News
Home / Science / We celebrate the father of the predictive algorithm – Quartz

We celebrate the father of the predictive algorithm – Quartz

If you work or study in an area where math is used, then you almost certainly owe something to Carl Friedrich Gauss, the great German mathematician born 241 years ago. Architects and designers use his findings to measure the curvature of surfaces. Engineers use his discovery of discrete Fourier transform, a method of image and sound processing. Biologists use its formula of normal distribution to study patterns in nature.

Gauss is sometimes called the "prince of mathematicians" for all his incredible finds. The breadth of Gauss achievements is highlighted in today's Google Doodle.

Gauss was so prolific that he considered his invention of statistical regression, a central tool in modern statistics and data science, too trivial to ever report when he discovered it. In particular, Gauss invented least squares regression, a method for calculating a straight line that best fits a set of data, and the earliest form of regression analysis. It is mainly used to understand the relationship between variables or to predict future results. For example, you could use regression to understand the strength of the relationship between parental size and the size of children, or even the parental size and income of children as they grow up.

Although French mathematician Adrien-Marie Legendre first used the regression in 1

805 to publish a paper, Gauss claimed to have invented the method in 1795. He claimed his discovery in a 1809 paper in which he used regression to predict the position of an asteroid. Legendre denied that Gauss deserved credit for the invention, and it would lead to life-long animosity between the two. However, as the historian Stephen Stigler explains in a paper on Confusion (pdf), Gauss would receive the most awards because he has done more to explain the fundamental value of regression. He also provided an algorithm to calculate it.

Gauss and Legendre never used the term regression for their method. It was first described in 1901 by statistician Karl Pearson as a "regression line".

Regression today is one of the foundations of modern social science and is one of the most important tools of computer science. It's been evolving since Gauss's time, of course, but the fundamentals are still pretty similar. It is used by economists to understand what causes economic growth, by psychologists to analyze experiments on human behavior, and by biostatisticians to find out which medicines to use safely.

Machines also use regression to forecast things like what ads show on a webpage. While newer prediction algorithms, such as support vector machines and neural networks, generally outperform least-squares accuracy, the method remains popular because of its simplicity and speed of calculation. More than 200 years later, Gauss' work is as relevant as ever.

// chart clock var _sf_async_config = { UID: 55570 }; (Function(){ Function loadChartbeat () { window._sf_endpt = (new date ()). getTime (); var e = document.createElement (& # 39; script & # 39;); e.setAttribute (& # 39; src & # 39; https: //a248.e.akamai.net/chartbeat.download.akamai.com/102508/js/chartbeat.js&#39;); document.body.appendChild (e); } var oldonload = window.onload; window.onload = (typeof window.onload! = & # 39; function & # 39;)? loadChartbeat: function () {oldonload (); loadChartbeat (); }; }) ();

// Bizo var _bizo_data_partner_id = "1016"; (Function(){ var b, a, u; a = document.createElement ("script"); a.type = "Text / Javascript"; a.async = true; u = "https://sjs.bizographics.com/insight.min.js"; a.src = u; b = document.getElementsByTagName ("script") [0]; back b.parentNode.insertBefore (a, b); }) ();

// Comscore var _comscore = _comescore || []; _comescore.push ({c1: "2", c2: "6463921"}); (Function {) { var s = document.createElement ("script"), el = document.getElementsByTagName ("script") [0]; s.async = true; s.src = "https://sb.scorecardresearch.com/beacon.js"; el.parentNode.insertBefore (s, el); }) ();

// Facebook ! Function (f, b, e, v, n, t, s) { when (f.fbq) returns; n = f.fbq = function () { n.callMethod? n.callMethod.apply (n, arguments): n.queue.push (arguments) }; if (! f._fbq) f._fbq = n; n.push = n; n.loaded =! 0; n.version = & # 39; 2.0 & # 39 ;; n.queue = []; t = b.createElement (e); t.async =! 0; t.src = v; s = b.getElementsByTagName (s) [0]; s.parentNode.insertBefore (t, s) } (Window, document, & # 39; script & # 39 ;, & # 39; https: //connect.facebook.net/en_US/fbevents.js&#39;);

fbq (& # 39; init & # 39 ;, 1416115438681460 & # 39;); fbq (& # 39; trackCustom & # 39 ;, & # 39; PixelInitialized & # 39 ;, {});

// Quora ! Function (q, e, v, n, t, s) {if (q.qp) return; n = q.qp = function () {n.qp? n.qp.apply (n, arguments): n.queue.push (arguments);}; n.queue = []; t = document.createElement (s); t.async =! 0; t.src = v; s = document.getElementsByTagName (s) [0]; s.parentNode.insertBefore (t, s);} (window, & # 39; script & # 39 ;, https: //a.quora.com/qevents.js&#39;); qp (& # 39; init & # 39 ;, 82a7ff2dce8345b9b1b534377870fd50 & # 39;); qp (& # 39; track & # 39 ;, & # 39; ViewContent & # 39;);