?url_ver=Z39.88-2004&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Adc&rft.title=PENERAPAN+ARTIFICAL+NEURAL+NETWORK+ALGORITMA%0D%0ABACKPROPAGATION+DALAM+MEMPREDIKSI+HARGA+EMAS&rft.creator=DWI+OKTAVIA%2C+1717031015&rft.subject=500+ilmu+pengetahuan+alam+dan+matematika&rft.description=Time+Series+adalah+pengamatan+pada+suatu+variabel+dari+waktu+lampau+dan+dicatat%0D%0Asecara+berurutan+menurut+urutan+waktu+dengan+periode+yang+tetap.+Data+dari+waktu%0D%0Alampau+harga+emas+merupakan+salah+satu+data+time+series.+Pada+umumnya+orang%0D%0Amemilih+berinvestasi+dalam+bentuk+emas+untuk+memperoleh+keuntungan.+Tujuan%0D%0Adari+penelitian+ini+adalah+menjelaskan+prosedur+pembentukan+model+Feedforward%0D%0ANeural+Network+(FFNN)+dengan+Algoritma+Backpropagation+(BP)+dan%0D%0Ameramalkan+harga+emas+menggunakan+model+tersebut.%0D%0AProses+pembentukan+model+Feedforward+neural+network+dengan+algoritma%0D%0ABackpropagation+pada+data+time+series+terdiri+atas+beberapa+tahap%2C+yaitu+(1)%0D%0Amenentukan+input+berdasarkan+plot+ACF+dan+PACF%2C+(2)+melakukan+pembagian+data%0D%0Amenjadi+2+yaitu+data+training+dan+data+testing%2C+(3)+menormalisasi+data%2C+(4)%0D%0Amembangun+model+Feedforward+neural+network+dengan+algoritma%0D%0ABackpropagation%2C+yaitu+menentukan+jumlah+neuron+pada+lapis+tersembunyi+dan%0D%0Amenentukan+bobot+model%2C+(5)+denormalisasi+dan+(6)+uji+kesesuaian+model.+Langkah%0D%0Atersebut+menghasilkan+model+yang+terbaik%2C+yang+dapat+digunakan+untuk+peramalan.%0D%0AModel+FFNN+dengan+algoritma+BP+ini+diterapkan+pada+data+harga+emas+bulan%0D%0AFebruari+2013+sampai+Februari+2021+dengan+variabel+inputnya+yaitu+harga+emas%0D%0Adunia.+Struktur+jaringan+terbaik+yang+diperoleh+adalah+dengan+3+neuron+input%2C+5%0D%0Aneuron+pada+hidden+layer+1%2C+dan+4+neuron+pada+hidden+layer+2+dengan%0D%0Amenggunakan+fungsi+aktivasi+Tanh.+Hasil+peramalan+harga+emas+untuk+10+periode%0D%0Ake+depan+menghasilkan+error+terkecil+pada+9+Februari+2021+yaitu+sebesar+1.491%2C+dan%0D%0Aerror+terbesar+pada+tanggal+5+Februari+2021+sebesar+47.518+dengan+menghasilkan%0D%0AMAPE+sebesar+0.74%25.%0D%0AKata+kunci+%3A+Feedforward+Neural+Network%2C+Backpropagation%2C+peramalan%2C+harga%0D%0A%0D%0Aemas+Time+Series+is+an+observation+on+a+variable+from+the+past+and+recorded+sequentially%0D%0Aaccording+to+the+time+sequence+with+a+fixed+period.+In+general%2C+people+choose+to%0D%0Ainvest+in+gold+to+make+a+profit.+The+purpose+of+this+study+is+to+explain+the+procedure%0D%0Afor+establishing+a+Feedforward+Neural+Network+(FFNN)+model+with+the%0D%0ABackpropagation+Algorithm+(BP)+and+predicting+the+price+of+gold+using+this+model.%0D%0AThe+process+of+forming+a+Feedforward+neural+network+model+with+the%0D%0ABackpropagation+algorithm+on+time+series+data+consists+of+several+stages%2C+namely%0D%0A(1)+determining+the+input+based+on+the+ACF+and+PACF+plots%2C+(2)+dividing+the+data%0D%0Ainto+2%2C+namely+training+data+and+testing+data%2C+(3)+normalizing+the+data.+%2C+(4)+build+a%0D%0AFeedforward+neural+network+model+with+the+Backpropagation+algorithm%2C+which%0D%0Adetermines+the+number+of+neurons+in+the+hidden+layer+and+determines+the+weight+of%0D%0Athe+model%2C+(5)+denormalization+and+(6)+model+suitability+test.+This+step+produces%0D%0Athe+best+model%2C+which+can+be+used+for+forecasting.%0D%0AThe+FFNN+model+with+the+BP+algorithm+is+applied+to+gold+price+data+from+February%0D%0A2013+to+February+2021+with+the+input+variable%2C+namely+the+world+gold+price.+The%0D%0Abest+network+structure+obtained+is+with+3+input+neurons%2C+5+neurons+in+hidden+layer%0D%0A1%2C+and+4+neurons+in+hidden+layer+2+using+the+Tanh+activation+function.+The+results%0D%0Aof+forecasting+gold+prices+for+the+next+10+periods+produced+the+smallest+error+on%0D%0AFebruary+9%2C+2021%2C+which+was+1.491%2C+and+the+largest+error+on+February+5%2C+2021%2C%0D%0Aamounted+to+47.518+by+producing+a+MAPE+of+0.74%25.%0D%0AKeywords%3A+Feedforward+Neural+Network%2C+Backpropagation%2C+forecasting%2C+gold+price&rft.publisher=FAKULTAS+MATIMATIKA+DAN+ILMU+PENGETAHUAN+ALAM&rft.date=2021&rft.type=Skripsi&rft.type=NonPeerReviewed&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F62422%2F1%2F1.%2520ABSTRAK-ABSTRACT%2520-%2520Rocket%2520Digital_29.pdf&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F62422%2F2%2F2.%2520SKRIPSI%2520FULL%2520-%2520Rocket%2520Digital_41.pdf&rft.format=text&rft.identifier=http%3A%2F%2Fdigilib.unila.ac.id%2F62422%2F3%2F3.%2520SKRIPSI%2520TANPA%2520BAB%2520PEMBAHASAN%2520-%2520Rocket%2520Digital_38.pdf&rft.identifier=++DWI+OKTAVIA%2C+1717031015++(2021)+PENERAPAN+ARTIFICAL+NEURAL+NETWORK+ALGORITMA+BACKPROPAGATION+DALAM+MEMPREDIKSI+HARGA+EMAS.++FAKULTAS+MATIMATIKA+DAN+ILMU+PENGETAHUAN+ALAM%2C+UNIVERSITAS+LAMPUNG.+++++&rft.relation=http%3A%2F%2Fdigilib.unila.ac.id%2F62422%2F