{"id":2739,"date":"2019-12-17T16:29:05","date_gmt":"2019-12-17T16:29:05","guid":{"rendered":"http:\/\/34.74.67.11\/?page_id=2739"},"modified":"2020-01-17T16:16:37","modified_gmt":"2020-01-17T16:16:37","slug":"build-and-deploy","status":"publish","type":"page","link":"https:\/\/www.iventura.ai\/index.php\/build-and-deploy\/","title":{"rendered":"Solutions"},"content":{"rendered":"

\n
\n\n\t

Credit Card Fraud Detection<\/h3>\n<\/div>\n
<\/p>\n

Use Case:<\/strong><\/h4>\n<\/p>\n
    \n
  1. 1.) Credit card companies are able to recognize fraudulent credit card transactions so that customers are not charged for items that they did not purchase.<\/li>\n
  2. 2.) The Objective is anonymized credit card transactions labeled as fraudulent or genuine<\/li>\n<\/ol>\n

    \n<\/div><\/div><\/div><\/div>

    <\/p>\n

    Solution:<\/strong><\/h4>\n<\/p>\n
      \n
    • 1) The class datasets is type of unbalanced classification.<\/li>\n
    • 2) Thus, SMOTE is used for imbalanced labelled data.<\/li>\n
    • 3) Exploratory data analysis is carried out on feature input data.<\/li>\n
    • 4) Class data contains two classes fraudulent and not fraudulent.<\/li>\n
    • 5) Logistic regression with balanced class is used to predict fraudulent of credit card.<\/li>\n<\/ul>\n

      \n<\/div><\/div><\/div>

      \n\n \"\" <\/div>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/section>
      \n
      \n\n\t

      Revenue Forecasting<\/h3>\n<\/div>\n
      <\/p>\n

      Use Case:<\/strong><\/h4>\n<\/p>\n
        \n
      • 1) Company fetches the financial data from various clients as individual excel sheets. These sheets are then clubbed as zip file. From empirical model sheet, data should be fetched and processed.<\/span><\/li>\n
      • 2) The objective is to forecast sales of revenues from empirical sheet based on past sales.<\/span><\/li>\n<\/ul>\n

        \n<\/div><\/div><\/div><\/div>

        \n\n \"\" <\/div>\n<\/div><\/div>
        <\/p>\n

        Solution:<\/strong><\/h4>\n<\/p>\n
          \n
        • 1) After extracting files,\u00a0 data preprocessing is done. Stationarity of revenue is checked to describe future behavior.<\/li>\n
        • 2) fbprophet is applied on dataset to reach objective.<\/li>\n<\/ul>\n

          \n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/section>

          \n
          \n\n\t

          Sentiment Analysis for drugs\/medicines<\/h3>\n<\/div>\n
          <\/p>\n

          Use Case:<\/strong><\/h4>\n<\/p>\n
            \n
          • Data contain samples of text. This text can contain one or more drug mentions. Each row contains a unique combination of the text and the drug mention.\u00a0 <\/span>The Objective is to predict the sentiment for texts contained in the test dataset for given the text and drug n<\/li>\n<\/ul>\n

            \n<\/div><\/div><\/div><\/div>

            <\/p>\n

            Solution:<\/strong><\/h4>\n<\/p>\n
              \n
            • 1) Input Dataset is “text\". The unstructured data is processed with raw data preprocessing followed by text preprocessing .\u00a0<\/span><\/li>\n
            • 2) TFIDF featurization is used to convert preprocessed text into vectors.\u00a0<\/span><\/li>\n
            • 3) Sentiment class data is imbalanced .<\/span><\/li>\n
            • 4) Thus, Sentiment Class data is performed over-sampling using SMOTE.<\/span><\/li>\n
            • 5) The misclassification error for each alpha value is plotted and best alpha value is used in Naive Bayes classifier .\u00a0<\/span><\/li>\n
            • 6) The plotted confusion matrix is evaluated based on naive bayes classifier.<\/span><\/li>\n<\/ul>\n

              \n<\/div><\/div><\/div>

              \n\n \"\" <\/div>\n<\/div><\/div><\/div><\/div><\/div><\/div><\/div><\/section><\/p>\n","protected":false},"excerpt":{"rendered":"","protected":false},"author":1,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"tpl-king-composer.php","meta":{"footnotes":""},"yst_prominent_words":[145,177,180,168,178,144,179,164,161,175,183,173,176,174,181,182,143,139,148,134],"class_list":["post-2739","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/pages\/2739","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/users\/1"}],"replies":[{"embeddable":true,"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/comments?post=2739"}],"version-history":[{"count":1,"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/pages\/2739\/revisions"}],"predecessor-version":[{"id":3584,"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/pages\/2739\/revisions\/3584"}],"wp:attachment":[{"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/media?parent=2739"}],"wp:term":[{"taxonomy":"yst_prominent_words","embeddable":true,"href":"https:\/\/www.iventura.ai\/index.php\/wp-json\/wp\/v2\/yst_prominent_words?post=2739"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}