{
  "fetched_at": "2026-10-22T07:40:39Z",
  "source_url": "https://www.kaggle.com/competitions/facebook-ad-campaign-budget-prediction/data",
  "pages": [
    {
      "name": "data-description",
      "content": "Explanation of columns:\n\nAd_ID: Unique identifier for each ad.\nAd_Creative: Description of the ad content (text, image, video, carousel, etc.).\nTarget_Demographics: Age and gender targeting criteria for the ad.\nTarget_Interests: Interests targeting criteria for the ad.\nLocation: Targeted location for the ad campaign.\nImpressions: Number of times the ad was displayed.\nClicks: Number of clicks on the ad.\nConversions: Number of users who completed the desired action (e.g., made a purchase) after clicking the ad.\nBudget_Spent: Amount spent on the campaign.\nPlease note that this is a basic example, and a more comprehensive dataset would include additional features and variability. In a real-world scenario, you would have a more extensive dataset with a larger number of ads, diverse targeting criteria, and a broader range of performance metrics.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Description",
      "content": "Participants will be provided with historical data from Facebook advertising campaigns, including information about the ad creative, targeting parameters, and performance metrics. The goal is to develop a predictive model that can accurately estimate the budget required for a new advertising campaign based on the given features.\n\n**Data**:\nThe dataset will include information such as:\n\n- Ad creative details (images, text, format).\n- Targeting parameters (demographics, interests, location).\n- Ad performance metrics (impressions, clicks, click-through rate, conversion rate).\nBudget and spending details for previous campaigns.\n- Participants will need to preprocess the data, perform feature engineering, and build a regression model to predict the budget for a new campaign.\n\n**Prizes**:\nKaggle competitions typically offer cash prizes, Kaggle swag, and recognition on the Kaggle platform for top-performing participants.\n\n**Benefits**:\n\n1. **Practical Application**: Predicting campaign budgets is a real-world problem faced by digital marketers, making the competition relevant to industry needs.\n2. **Data Analysis Skills**: Participants will enhance their skills in preprocessing data, feature engineering, and regression modeling.\n3. **Insights for Marketers**: The competition results could provide valuable insights into the factors that most influence Facebook ad campaign budgets.\nThis competition aligns with the growing importance of data-driven decision-making in digital marketing and can attract participants interested in both machine learning and marketing domains.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "Evaluation",
      "content": "Submissions will be evaluated based on the accuracy of the budget predictions. The competition can use performance metrics like Mean Absolute Error (MAE) or Root Mean Squared Error (RMSE) to measure how well the models predict the actual campaign budgets.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "rules",
      "content": "Competition Rules: Facebook Ad Campaign Budget Prediction\n\nObjective:\n\nDevelop a machine learning model to predict the budget required for a Facebook advertising campaign based on provided historical data.\nData:\n\nParticipants will be provided with a training dataset containing information on ad creatives, targeting parameters, ad performance metrics, and actual budget spent.\nSubmission Format:\n\nSubmissions must be in CSV format.\nEach submission should include Ad_ID and the corresponding Predicted_Budget column.\nEvaluation:\n\nSubmissions will be evaluated based on the accuracy of the predicted budgets compared to the actual budgets.\nThe evaluation metric will be Mean Absolute Error (MAE).\nModel Training:\n\nParticipants are free to use any machine learning algorithms or frameworks.\nOverfitting to the specific training dataset is discouraged.\nData Usage:\n\nParticipants should only use the provided training dataset for model training.\nExternal data sources are not allowed.\nTeam Size:\n\nTeams can have a maximum of 3 members.\nCode Submission:\n\nParticipants must submit the code used to train their models.\nThe code should be well-documented for reproducibility.\nPrizes:\n\nCash prizes will be awarded to the top-performing teams.\nRecognition on the Kaggle platform and social media.\nTimeline:\n\nThe competition will have a defined start and end date.\nLate submissions may not be considered.\nCode of Conduct:\n\nParticipants are expected to follow Kaggle's code of conduct.\nPlagiarism and any form of cheating will result in disqualification.\nOrganizer's Decision:\n\nThe organizer's decision on winners and rule interpretation is final.\nBy participating in the competition, participants agree to abide by these rules. The rules may be subject to updates or changes, and participants should regularly check for any announcements or clarifications from the organizers.",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    },
    {
      "name": "abstract",
      "content": "Facebook Ad Budget Predictor: Forecast campaign spend based on historical data. Optimize ad performance with a predictive model. #DataScience #PredictiveAnalytics #KaggleCompetition",
      "isPublished": false,
      "hasIsPublished": false,
      "postTitle": "",
      "hasPostTitle": false,
      "mimeType": "",
      "hasMimeType": false
    }
  ]
}