Abstract-The number of internet users worldwide is growing and will continue to grow along with the advancement of communication technologies. Media marketing products and services not only in the print media and electronic media but also on the internet. The Internet can be over the limit State being one of the power of the internet as a marketing medium. Moreover, the cost is relatively cheap. The penetration of the internet as a marketing medium lasts for 24 hours in parts of the world. But make the internet sites visited isn't quite easy because of the need to be a certain dibagian-bagian optimization. Optimization on the website better known as SEO (Search Engine Optimization) which is an important rule in order to make internet sites more searchable with keywords that users want. By applying the website then SEO can appear on the first page of the disbursement and thus expected traffic visitors also increased as well as in media promotions can boost sales figures.

Penelitian ini bertujuan untuk mengembangkan perangkat lunak Sistem Informasi Berbasis Web di rumah sakit. Sebagai sebuah sistem yang dapat memberikan informasi yang diperlukan dengan mudah dan kemudian diimplementasikan dalam bentuk program. penelitian ini dilakukan dengan metode analisis, desain dan pembuatan program. Aplikasi yang dikembangkan oleh Web, menggunakan database MySQL dan SMS Gateway. Hal ini dapat berguna untuk pasien yang ingin berobat di rumah sakit.

Menjaga persediaan barang agar barang tidak sampai kosong termasuk salah satu menjaga kepuasan pelanggan. Untuk melaksanakan hal tersebut manajemen perusahaan harus dapat menganalisa mana barang yang laku dan mana barang yang kurang laku, khususnya pada bagian penjualan. Hal ini tidak mudah bagi CV. Muria PS dikarenakan memiliki jumlah item barang yang cukup banyak, sehingga dibutuhkan sedikit teknik komputasi untuk mempermudah permasalahan tersebut. Algoritma K-Means clustering dipilih dalam mengatasi permasalahan tersebut karena mampu mengelompokkan produk yang terjual dan masih tersedia menjadi beberapa cluster. Dari tiga cluster yang dibentuk menghasilkan cluster 1 terdiri dua barang, cluster 2 terdiri 9 barang dan sisanya dari 25 barang masuk pada cluster 3. Dari hasil ini bisa dimanfaatkan oleh manajemen CV. Muria PS untuk meningkatkan stok persediaan barang dan strategi penjualannya.

Promotion is necessary for every business field, including server of reload pulsa. In the strategy of promotion, one of the necessary thing is how the data distribution of the customer and its characteristics. One method that can be applied to explore the distribution of customers and transaction characteristics is to group customers using clustering algorithm technique. The technique of clustering algorithm is suitable to be applied because it can bring up some groups that have previously unknown attributes. Thus it can be used as new knowledge for the owner to be used according to needs. This data training take attributes such as customer, transaction amount, and address. The number of centroid specified amounts to 3. The grouping results stop at the 4th iteration with the ratio value 0.0553 in the 3rd and 4th iterations. From the result of iteration then formed 3 groups namely: C1 {C,

The car logo itself is very distinguishing in a car is a vehicle logo that serves to introduce to the public about their brand. This will also create its own appeal to the public in knowing the existing car logo. Types in study aims to classify for car logos in Indonesia. So that later people will understand in choosing a car with a quality brand. From the results obtained that the Decision Tree at split ratio 50:50 precision gets a value of 0.604, recall gets a value of 0.611, f-measure gets a value of 0.598 and accuracy gets a value of 95.70% at comparing data testing and training 50:50. Then the tests carried out by ANNbackpropagation resulted in a split ratio of 50:50 texture and shape features with a precision value reaching 0.680, recall getting a value of 0.521, f-measurement getting a value of 0.600 and accuracy also having the highest value generated by ANNbackpropagation reaching 92.50% at comparing data testing and training 50:50. The results prove that the classification using Decision Tree produces the highest accuracy, precision, recall, and f-measure compared to the decision tree.