Essec\Faculty\Model\Contribution {#2216
  #_index: "academ_contributions"
  #_id: "11969"
  #_source: array:26 [
    "id" => "11969"
    "slug" => "lstm-response-models-for-direct-marketing-analytics-replacing-feature-engineering-with-deep-learning"
    "yearMonth" => "2021-02"
    "year" => "2021"
    "title" => "LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning"
    "description" => "SARKAR, M. et DE BRUYN, A. (2021). LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning. <i>Journal of Interactive Marketing</i>, 53(February), pp. 80-95."
    "authors" => array:2 [
      0 => array:3 [
        "name" => "DE BRUYN Arnaud"
        "bid" => "B00024825"
        "slug" => "de-bruyn-arnaud"
      ]
      1 => array:1 [
        "name" => "SARKAR Mainak"
      ]
    ]
    "ouvrage" => ""
    "keywords" => array:6 [
      0 => "Long-short term memory neural network (LSTM)"
      1 => "Recurrent neural network (RNN)"
      2 => "Feature engineering"
      3 => "Response model"
      4 => "Panel data"
      5 => "Direct marketing"
    ]
    "updatedAt" => "2023-07-10 16:44:08"
    "publicationUrl" => "https://doi.org/10.1016/j.intmar.2020.07.002"
    "publicationInfo" => array:3 [
      "pages" => "80-95"
      "volume" => "53"
      "number" => "February"
    ]
    "type" => array:2 [
      "fr" => "Articles"
      "en" => "Journal articles"
    ]
    "support_type" => array:2 [
      "fr" => "Revue scientifique"
      "en" => "Scientific journal"
    ]
    "countries" => array:2 [
      "fr" => null
      "en" => null
    ]
    "abstract" => array:2 [
      "fr" => "In predictive modeling, firms often deal with high-dimensional data that span multiple channels, websites, demographics, purchase types, and product categories. Traditional customer response models rely heavily on feature engineering, and their performance depends on the analyst's domain knowledge and expertise to craft relevant predictors. As the complexity of data increases, however, traditional models grow exponentially complicated. In this paper, we demonstrate that long-short term memory (LSTM) neural networks, which rely exclusively on raw data as input, can predict customer behaviors with great accuracy. In our first application, a model outperforms standard benchmarks. In a second, more realistic application, an LSTM model competes against 271 hand-crafted models that use a wide variety of features and modeling approaches. It beats 269 of them, most by a wide margin. LSTM neural networks are excellent candidates for modeling customer behavior using panel data in complex environments (e.g., direct marketing, brand choices, clickstream data, churn prediction)."
      "en" => "In predictive modeling, firms often deal with high-dimensional data that span multiple channels, websites, demographics, purchase types, and product categories. Traditional customer response models rely heavily on feature engineering, and their performance depends on the analyst's domain knowledge and expertise to craft relevant predictors. As the complexity of data increases, however, traditional models grow exponentially complicated. In this paper, we demonstrate that long-short term memory (LSTM) neural networks, which rely exclusively on raw data as input, can predict customer behaviors with great accuracy. In our first application, a model outperforms standard benchmarks. In a second, more realistic application, an LSTM model competes against 271 hand-crafted models that use a wide variety of features and modeling approaches. It beats 269 of them, most by a wide margin. LSTM neural networks are excellent candidates for modeling customer behavior using panel data in complex environments (e.g., direct marketing, brand choices, clickstream data, churn prediction)."
    ]
    "authors_fields" => array:2 [
      "fr" => "Marketing"
      "en" => "Marketing"
    ]
    "indexedAt" => "2024-11-21T08:21:48.000Z"
    "docTitle" => "LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning"
    "docSurtitle" => "Journal articles"
    "authorNames" => "<a href="/cv/de-bruyn-arnaud">DE BRUYN Arnaud</a>, SARKAR Mainak"
    "docDescription" => "<span class="document-property-authors">DE BRUYN Arnaud, SARKAR Mainak</span><br><span class="document-property-authors_fields">Marketing</span> | <span class="document-property-year">2021</span>"
    "keywordList" => "<a href="#">Long-short term memory neural network (LSTM)</a>, <a href="#">Recurrent neural network (RNN)</a>, <a href="#">Feature engineering</a>, <a href="#">Response model</a>, <a href="#">Panel data</a>, <a href="#">Direct marketing</a>"
    "docPreview" => "<b>LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning</b><br><span>2021-02 | Journal articles </span>"
    "docType" => "research"
    "publicationLink" => "<a href="https://doi.org/10.1016/j.intmar.2020.07.002" target="_blank">LSTM Response Models for Direct Marketing Analytics: Replacing Feature Engineering with Deep Learning</a>"
  ]
  +lang: "en"
  +"_type": "_doc"
  +"_score": 8.613594
  +"parent": null
}