Insurance Claim Approval Dataset<\/strong><\/a><\/p>\n# Step 1: Import required libraries\r\nimport pandas as pd\r\nfrom sklearn.model_selection import train_test_split\r\nfrom sklearn.preprocessing import LabelEncoder\r\nfrom xgboost import XGBClassifier\r\nfrom sklearn.metrics import accuracy_score, confusion_matrix\r\nimport matplotlib.pyplot as plt\r\n\r\n# Step 2: Load dataset\r\ndf = pd.read_csv(\"D:\/\/scikit_data\/insurancedata\/insurance_claim_approval.csv\")\r\ndf.head()\r\ndf.isnull().sum()\r\ndf.shape\r\n\r\n# Step 3: Encode categorical features\r\nlabel_encoders = {}\r\nfor col in [\"Gender\", \"Smoking\", \"PolicyType\", \"PreExistingCondition\"]:\r\n le = LabelEncoder()\r\n df[col] = le.fit_transform(df[col])\r\n label_encoders[col] = le # Save encoders for later use\r\ndf.head()\r\n\r\n# Step 4: Split features and target\r\nX = df.drop(\"ClaimApproved\", axis=1) # Input Data\r\ny = df[\"ClaimApproved\"] # output\r\n\r\n# Step 5: Train-test split\r\nX_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)\r\nlen(X_test)\r\n\r\n# Step 6: Initialize and train XGBoost model\r\nmodel = XGBClassifier(use_label_encoder=False, eval_metric='logloss')\r\nmodel.fit(X_train, y_train)\r\n\r\n# Step 7: Predictions and Evaluation\r\ny_pred = model.predict(X_test)\r\nacc = accuracy_score(y_test, y_pred)\r\ncm = confusion_matrix(y_test, y_pred)\r\n\r\nprint(\" Model Accuracy:\", round(acc * 100, 2), \"%\")\r\nprint(\"Confusion Matrix:\\n\", cm)\r\n\r\n# Step 9: User Input Prediction\r\nprint(\"\\n Enter details to predict claim approval:\")\r\n\r\nage = int(input(\"Age: \"))\r\ngender = input(\"Gender (Male\/Female): \")\r\nbmi = float(input(\"BMI: \"))\r\nsmoking = input(\"Smoking (Yes\/No): \")\r\npolicy = input(\"Policy Type (Basic\/Premium\/Gold): \")\r\namount = float(input(\"Claim Amount: \"))\r\ncondition = input(\"Pre-existing Condition (None\/Diabetes\/Heart Disease\/Asthma): \")\r\nstay = int(input(\"Hospital Stay Days: \"))\r\n\r\n# Encode user inputs\r\ngender = label_encoders[\"Gender\"].transform([gender])[0]\r\nsmoking = label_encoders[\"Smoking\"].transform([smoking])[0]\r\npolicy = label_encoders[\"PolicyType\"].transform([policy])[0]\r\ncondition = label_encoders[\"PreExistingCondition\"].transform([condition])[0]\r\n\r\ninput_data = pd.DataFrame([{\r\n \"Age\": age,\r\n \"Gender\": gender,\r\n \"BMI\": bmi,\r\n \"Smoking\": smoking,\r\n \"PolicyType\": policy,\r\n \"ClaimAmount\": amount,\r\n \"PreExistingCondition\": condition,\r\n \"HospitalStayDays\": stay\r\n}])\r\n\r\n# Predict\r\nprediction = model.predict(input_data)[0]\r\nprint(\"\\n Claim Status:\", \" Approved\" if prediction == 1 else \" Not Approved\")\r\n\r\n# Step 8: Feature Importance Plot\r\nplt.figure(figsize=(10, 6))\r\nplt.barh(X.columns, model.feature_importances_, color='skyblue')\r\nplt.title(\" Feature Importance - Claim Approval\")\r\nplt.xlabel(\"Importance Score\")\r\nplt.tight_layout()\r\nplt.show()\r\n<\/pre>\n<\/span><\/p>\n","protected":false},"excerpt":{"rendered":"Program 1 Insurance Claim Approval Dataset # Step 1: Import required libraries import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from xgboost import XGBClassifier from sklearn.metrics import accuracy_score, confusion_matrix import...<\/p>\n","protected":false},"author":581,"featured_media":0,"comment_status":"open","ping_status":"closed","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[36],"tags":[34938,34936,34935,34934,8431,34937,33127,33128,20697],"class_list":["post-146019","post","type-post","status-publish","format-standard","hentry","category-machine-learning","tag-insurance-claim-approval","tag-insurance-claim-approval-project","tag-insurance-claim-approval-using-machine-learning","tag-insurance-claim-approval-using-xgboost","tag-machine-learning","tag-machine-learning-insurance-claim-approval-using-xgboost","tag-machine-learning-practical","tag-machine-learning-program","tag-machine-learning-project"],"yoast_head":"\n
ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm - DataFlair<\/title>\n<meta name=\"robots\" content=\"index, follow, max-snippet:-1, max-image-preview:large, max-video-preview:-1\" \/>\n<link rel=\"canonical\" href=\"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/\" \/>\n<meta property=\"og:locale\" content=\"en_US\" \/>\n<meta property=\"og:type\" content=\"article\" \/>\n<meta property=\"og:title\" content=\"ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm - DataFlair\" \/>\n<meta property=\"og:description\" content=\"Program 1 Insurance Claim Approval Dataset # Step 1: Import required libraries import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from xgboost import XGBClassifier from sklearn.metrics import accuracy_score, confusion_matrix import...\" \/>\n<meta property=\"og:url\" content=\"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/\" \/>\n<meta property=\"og:site_name\" content=\"DataFlair\" \/>\n<meta property=\"article:publisher\" content=\"https:\/\/www.facebook.com\/DataFlairWS\/\" \/>\n<meta property=\"article:published_time\" content=\"2025-07-21T05:53:14+00:00\" \/>\n<meta name=\"author\" content=\"DataFlair Team\" \/>\n<meta name=\"twitter:card\" content=\"summary_large_image\" \/>\n<meta name=\"twitter:creator\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:site\" content=\"@DataFlairWS\" \/>\n<meta name=\"twitter:label1\" content=\"Written by\" \/>\n\t<meta name=\"twitter:data1\" content=\"DataFlair Team\" \/>\n\t<meta name=\"twitter:label2\" content=\"Est. reading time\" \/>\n\t<meta name=\"twitter:data2\" content=\"1 minute\" \/>\n<!-- \/ Yoast SEO plugin. -->","yoast_head_json":{"title":"ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm - DataFlair","robots":{"index":"index","follow":"follow","max-snippet":"max-snippet:-1","max-image-preview":"max-image-preview:large","max-video-preview":"max-video-preview:-1"},"canonical":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/","og_locale":"en_US","og_type":"article","og_title":"ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm - DataFlair","og_description":"Program 1 Insurance Claim Approval Dataset # Step 1: Import required libraries import pandas as pd from sklearn.model_selection import train_test_split from sklearn.preprocessing import LabelEncoder from xgboost import XGBClassifier from sklearn.metrics import accuracy_score, confusion_matrix import...","og_url":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/","og_site_name":"DataFlair","article_publisher":"https:\/\/www.facebook.com\/DataFlairWS\/","article_published_time":"2025-07-21T05:53:14+00:00","author":"DataFlair Team","twitter_card":"summary_large_image","twitter_creator":"@DataFlairWS","twitter_site":"@DataFlairWS","twitter_misc":{"Written by":"DataFlair Team","Est. reading time":"1 minute"},"schema":{"@context":"https:\/\/schema.org","@graph":[{"@type":"Article","@id":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/#article","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/"},"author":{"name":"DataFlair Team","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/c187795dc82ab948373cca526df7c445"},"headline":"ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm","datePublished":"2025-07-21T05:53:14+00:00","mainEntityOfPage":{"@id":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/"},"wordCount":13,"commentCount":0,"publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"keywords":["insurance claim approval","insurance claim approval project","insurance claim approval using machine learning","insurance claim approval using xgboost","machine learning","machine learning insurance claim approval using xgboost","machine learning practical","machine learning program","machine learning project"],"articleSection":["Machine Learning Tutorials"],"inLanguage":"en-US","potentialAction":[{"@type":"CommentAction","name":"Comment","target":["https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/#respond"]}]},{"@type":"WebPage","@id":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/","url":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/","name":"ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm - DataFlair","isPartOf":{"@id":"https:\/\/data-flair.training\/blogs\/#website"},"datePublished":"2025-07-21T05:53:14+00:00","breadcrumb":{"@id":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/#breadcrumb"},"inLanguage":"en-US","potentialAction":[{"@type":"ReadAction","target":["https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/"]}]},{"@type":"BreadcrumbList","@id":"https:\/\/data-flair.training\/blogs\/insurance-claim-approval-using-xgboost\/#breadcrumb","itemListElement":[{"@type":"ListItem","position":1,"name":"Blog Home","item":"https:\/\/data-flair.training\/blogs\/"},{"@type":"ListItem","position":2,"name":"Machine Learning Tutorials","item":"https:\/\/data-flair.training\/blogs\/category\/machine-learning\/"},{"@type":"ListItem","position":3,"name":"ML Project \u2013 Insurance Claim Approval using XGBoost Algorithm"}]},{"@type":"WebSite","@id":"https:\/\/data-flair.training\/blogs\/#website","url":"https:\/\/data-flair.training\/blogs\/","name":"DataFlair","description":"Learn Today. Lead Tomorrow.","publisher":{"@id":"https:\/\/data-flair.training\/blogs\/#organization"},"potentialAction":[{"@type":"SearchAction","target":{"@type":"EntryPoint","urlTemplate":"https:\/\/data-flair.training\/blogs\/?s={search_term_string}"},"query-input":{"@type":"PropertyValueSpecification","valueRequired":true,"valueName":"search_term_string"}}],"inLanguage":"en-US"},{"@type":"Organization","@id":"https:\/\/data-flair.training\/blogs\/#organization","name":"DataFlair","url":"https:\/\/data-flair.training\/blogs\/","logo":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/","url":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","contentUrl":"https:\/\/data-flair.training\/blogs\/wp-content\/uploads\/sites\/2\/2016\/07\/Data-Flair.png","width":106,"height":48,"caption":"DataFlair"},"image":{"@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/logo\/image\/"},"sameAs":["https:\/\/www.facebook.com\/DataFlairWS\/","https:\/\/x.com\/DataFlairWS","https:\/\/www.linkedin.com\/company\/dataflair-web-services-pvt-ltd\/","https:\/\/www.youtube.com\/user\/DataFlairWS"]},{"@type":"Person","@id":"https:\/\/data-flair.training\/blogs\/#\/schema\/person\/c187795dc82ab948373cca526df7c445","name":"DataFlair Team","image":{"@type":"ImageObject","inLanguage":"en-US","@id":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","url":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","contentUrl":"https:\/\/secure.gravatar.com\/avatar\/2302ebc438084d2f1f993edc1996a0aae01332e81f3227cba8df0c48ec010ca4?s=96&d=mm&r=g","caption":"DataFlair Team"},"description":"DataFlair Team provides high-impact content on programming, Java, Python, C++, DSA, AI, ML, data Science, Android, Flutter, MERN, Web Development, and technology. We make complex concepts easy to grasp, helping learners of all levels succeed in their tech careers.","url":"https:\/\/data-flair.training\/blogs\/author\/dfteam6\/"}]}},"amp_enabled":true,"_links":{"self":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146019","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/users\/581"}],"replies":[{"embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/comments?post=146019"}],"version-history":[{"count":4,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146019\/revisions"}],"predecessor-version":[{"id":146037,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/posts\/146019\/revisions\/146037"}],"wp:attachment":[{"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/media?parent=146019"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/categories?post=146019"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/data-flair.training\/blogs\/wp-json\/wp\/v2\/tags?post=146019"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}