# BAN 502 Shark Tank Summer 2021 — Data

来源：https://www.kaggle.com/competitions/ban-502-shark-summer-2021/data

本地 Meta Kaggle 快照；不是本次实时页面。

# Dataset Description

<p>In this competition you will build models to predict whether or not a pitch on the TV show "Shark Tank" made a deal with one or more investors on the show. The dataset that you are provided for building your models contains data from 551 pitches. The response variable is "Deal_Yes" which indicates whether or not a pitch results in a deal with an investor. The competition dataset contains 236 pitches. The response variable (and other related variables that would give away the value of the response variable) has been removed from this dataset. You will create predictions for the Deal_Yes variable on the competition dataset.</p>
<h2>File descriptions</h2>
<ul>
<li><strong>shark_student.csv</strong> - build your models on this dataset </li>
<li><strong>shark_competition.csv</strong> - you will be scored on performance on this dataset</li>
<li><strong>sampleSubmission.csv</strong> - a sample submission file in the correct format</li>
<p>You are provided the three files listed above. Develop models on the "ames_student.csv" dataset and submit your predictions on the data in the "ames_competition.csv" dataset. A sample of the format for your predictions is provided in the "sampleSubmission.csv" file.</p>
<p>The data is described in detail in the "DataDescription.txt" file. </p>
<p>The Predict_for_Kaggle.Rmd demonstrates how set-up your predictions submission for Kaggle </p>
<ul>