Low score - house price prediction

yatin · April 17, 2020, 9:53pm

after doing a lot of variation with the hyperparameters my model can only produce 60% score
please have a look at the code

github.com

yatin9988/Machine-and-Deep-Learning-Codes/blob/master/Neural Network Challenges/House Price Prediction.ipynb

{
 "cells": [
  {
   "cell_type": "code",
   "execution_count": 830,
   "metadata": {},
   "outputs": [],
   "source": [
    "import numpy as np\n",
    "import matplotlib.pyplot as plt\n",
    "import pandas as pd"
   ]
  },
  {
   "cell_type": "code",
   "execution_count": 831,
   "metadata": {},
   "outputs": [],
   "source": [
    "train = pd.read_csv('Train_Data.csv')\n",

This file has been truncated. show original

S18CRX0120 · April 18, 2020, 6:20am

Hey @yatin, i have gone thrugh your ipynb, you have done a great job. What you can do is tu use BatchNormalization and Dropout Layers, You are heading in right direction. Also this is kaggle challenge, now if you think you have explored everything, try to read notebooks of top kagglers, on kaggle challenge itself.

Hope this resolved your doubt.
Plz mark the doubt as resolved in my doubts section.

S18CRX0120 · April 22, 2020, 6:44pm

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.