\u00d6rne\u011fin, y\u0131l\u0131n ilk \u00fc\u00e7 ay\u0131nda belirli bir \u00fcr\u00fcn\u00fcn a\u015fa\u011f\u0131daki sat\u0131\u015flar\u0131n\u0131n oldu\u011funu varsayal\u0131m:<\/span> <\/p>\n Nisan sat\u0131\u015f tahmini, \u00f6nceki Mart ay\u0131n\u0131n ger\u00e7ek sat\u0131\u015flar\u0131na e\u015fit olacakt\u0131r:<\/span> <\/p>\n Bu y\u00f6ntem basit olmas\u0131na ra\u011fmen pratikte \u015fa\u015f\u0131rt\u0131c\u0131 derecede iyi sonu\u00e7 verme e\u011filimindedir.<\/span><\/p>\n Bu e\u011fitimde, R’de saf tahminlerin nas\u0131l ger\u00e7ekle\u015ftirilece\u011fine ili\u015fkin ad\u0131m ad\u0131m bir \u00f6rnek sunulmaktad\u0131r.<\/span><\/p>\n \u0130lk olarak hayali bir \u015firkette 12 ayl\u0131k sat\u0131\u015f verilerini girece\u011fiz:<\/span><\/p>\n Daha sonra, her ay i\u00e7in basit tahminler olu\u015fturmak i\u00e7in a\u015fa\u011f\u0131daki form\u00fclleri kullanaca\u011f\u0131z:<\/span><\/p>\n \u0130lk tahmin edilen de\u011fer i\u00e7in basit\u00e7e NA<\/strong> kulland\u0131\u011f\u0131m\u0131z\u0131 unutmay\u0131n.<\/span><\/p>\n Son olarak tahminlerin do\u011frulu\u011funu \u00f6l\u00e7meliyiz. Do\u011frulu\u011fu \u00f6l\u00e7mek i\u00e7in kullan\u0131lan iki yayg\u0131n \u00f6l\u00e7\u00fcm \u015funlar\u0131 i\u00e7erir:<\/span><\/p>\n Her iki \u00f6l\u00e7\u00fcm\u00fc de hesaplamak i\u00e7in a\u015fa\u011f\u0131daki kodu kullanabiliriz:<\/span><\/p>\n Ortalama mutlak y\u00fczde hatas\u0131 %9,898<\/strong> ve ortalama mutlak hata 3,45’tir.<\/strong><\/span><\/p>\n Bu tahminin yararl\u0131 olup olmad\u0131\u011f\u0131n\u0131 anlamak i\u00e7in onu di\u011fer tahmin modelleriyle kar\u015f\u0131la\u015ft\u0131rabilir ve \u00f6l\u00e7\u00fcm do\u011frulu\u011funun daha iyi mi yoksa daha k\u00f6t\u00fc m\u00fc oldu\u011funu g\u00f6rebiliriz.<\/span><\/p>\n Son olarak, her d\u00f6nemdeki ger\u00e7ek sat\u0131\u015flar ile saf sat\u0131\u015f tahminleri aras\u0131ndaki farklar\u0131 g\u00f6rselle\u015ftirmek i\u00e7in basit bir \u00e7izgi grafi\u011fi olu\u015fturabiliriz:<\/span> <\/p>\n Tahmin edilen sat\u0131\u015f \u00e7izgisinin asl\u0131nda ger\u00e7ek sat\u0131\u015f \u00e7izgisinin de\u011fi\u015ftirilmi\u015f bir versiyonu oldu\u011funu unutmay\u0131n.<\/span><\/p>\n Saf tahmin, cari d\u00f6nemdeki sat\u0131\u015flar\u0131n \u00f6nceki d\u00f6nemdeki sat\u0131\u015flara e\u015fit olaca\u011f\u0131n\u0131 \u00f6ng\u00f6rd\u00fc\u011f\u00fc i\u00e7in bekledi\u011fimiz \u015fey tam olarak budur.<\/span><\/p>\n R’de MAE nas\u0131l hesaplan\u0131r<\/a> Saf bir tahmin, belirli bir d\u00f6neme ili\u015fkin tahminin \u00f6nceki d\u00f6nemde g\u00f6zlemlenen de\u011fere e\u015fit oldu\u011fu tahmindir. \u00d6rne\u011fin, y\u0131l\u0131n ilk \u00fc\u00e7 ay\u0131nda belirli bir \u00fcr\u00fcn\u00fcn a\u015fa\u011f\u0131daki sat\u0131\u015flar\u0131n\u0131n oldu\u011funu varsayal\u0131m: Nisan sat\u0131\u015f tahmini, \u00f6nceki Mart ay\u0131n\u0131n ger\u00e7ek sat\u0131\u015flar\u0131na e\u015fit olacakt\u0131r: Bu y\u00f6ntem basit olmas\u0131na ra\u011fmen pratikte \u015fa\u015f\u0131rt\u0131c\u0131 derecede iyi sonu\u00e7 verme e\u011filimindedir. Bu e\u011fitimde, R’de saf tahminlerin nas\u0131l […]<\/p>\n","protected":false},"author":1,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[11],"tags":[],"class_list":["post-1630","post","type-post","status-publish","format-standard","hentry","category-rehber"],"yoast_head":"\n![\"\"](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/naive_forecast1.png\")
<\/p>\n![\"Saf](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/naive_forecast2.png\")
<\/p>\n 1. Ad\u0131m: Verileri girin<\/strong><\/span><\/h3>\n
#create vector to hold actual sales data<\/span>\nactual <- c(34, 37, 44, 47, 48, 48, 46, 43, 32, 27, 26, 24)\n<\/strong><\/pre>\n Ad\u0131m 2: basit tahminler olu\u015fturun<\/strong><\/span><\/h3>\n
#generate naive forecasts<\/span>\nforecast <- c(NA, actual[- length<\/span> (actual)])\n\n#view naive forecasts<\/span>\nforecast\n\n[1] NA 34 37 44 47 48 48 46 43 32 27 26\n<\/strong><\/pre>\n 3. Ad\u0131m: Tahmin do\u011frulu\u011funu \u00f6l\u00e7\u00fcn<\/strong><\/span><\/h3>\n
\n
#calculate MAPE\n<\/span>mean(abs((actual-forecast)\/actual), na. rm<\/span> = T<\/span> ) * 100\n\n[1] 9.898281\n\n#calculate MAE\n<\/span>mean(abs(actual-forecast), na. rm<\/span> = T<\/span> )\n\n[1] 3.454545\n<\/strong><\/pre>\n 4. Ad\u0131m: Tahmini g\u00f6rselle\u015ftirin<\/strong><\/span><\/h3>\n
#plot actual sales\n<\/span>plot(actual, type=' l<\/span> ', col = ' red<\/span> ', main=' Actual vs. Forecasted Sales<\/span> ',\n xlab=' Sales Period<\/span> ', ylab=' Sales<\/span> ')\n\n#add line for forecasted sales\n<\/span>lines(forecast, type=' l<\/span> ', col = ' blue<\/span> ')\n\n#add legend\n<\/span>legend(' topright<\/span> ', legend=c(' Actual<\/span> ', ' Forecasted<\/span> '),\n col=c(' red<\/span> ', ' blue<\/span> '), lty=1)\n<\/strong><\/pre>\n![\"R'de](\"https:\/\/statorials.org\/wp-content\/uploads\/2023\/08\/naifr1.png\")
<\/p>\n Ek kaynaklar<\/strong><\/span><\/h3>\n
R’de MAPE nas\u0131l hesaplan\u0131r<\/a>
MAPE i\u00e7in iyi bir de\u011fer olarak kabul edilen \u015fey nedir?<\/a><\/p>\n","protected":false},"excerpt":{"rendered":"