A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets

<table class="table-group" id="tab2"><tr><td><table class="table"><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr class="thead"><td class="align_left">Feature value</td><td class="align_center">Frequency</td><td class="align_center">Normalized number</td></tr><tr><td class="thead-hr" colspan="3"><hr/></td></tr><tr><td class="align_left">0</td><td class="align_center">3076333</td><td class="align_center">1</td></tr><tr><td class="align_left">1</td><td class="align_center">1040891</td><td class="align_center">0.338351</td></tr><tr><td class="align_left">2</td><td class="align_center">1309</td><td class="align_center">0.000420</td></tr><tr><td class="align_left">3</td><td class="align_center">17</td><td class="align_center">0</td></tr><tr><td class="align_left">4</td><td class="align_center">496</td><td class="align_center">0.000156</td></tr><tr><td class="align_left">5</td><td class="align_center">2635</td><td class="align_center">0.000851</td></tr><tr><td class="align_left"> 6</td><td class="align_center">1314</td><td class="align_center">0.000422</td></tr><tr class="table-tr"><td colspan="3"><hr class="tbody-hr"/></td></tr></table></td></tr></table>

The frequency and normalized value of different values of the feature <i>banner_pos</i>.

Computational Intelligence and Neuroscience

tab2

Table 2

Table 2: A New Approach for Mobile Advertising Click-Through Rate Estimation Based on Deep Belief Nets 