WEBVTT 00:01.590 --> 00:08.520 I hope you did well in the last project, which was, again, a classification project, now in this 00:08.520 --> 00:13.870 particular project we would again be applying classification but on an industry level project. 00:14.670 --> 00:19.890 So this project is regarding flooding of junk properties. 00:20.190 --> 00:27.810 So flooding the property as possibly junk beforehand can help businesses prioritize their efforts and 00:27.810 --> 00:34.990 focus them on more probable success rather than bogged down with the weight of unsaleable portfolios. 00:35.400 --> 00:43.410 So these property sellers, they are trying to fly certain properties which don't really get sold easily 00:43.650 --> 00:51.180 so that they can target on something which is more beneficial and could give success faster. 00:51.420 --> 00:57.780 So in this project, we will be making use of the data from the past operations where many properties 00:57.780 --> 01:01.500 were found to be junk after their porches for renovations. 01:02.070 --> 01:10.920 So this particular dataset contains around sixty two thousand drawers of data and it has around 31 various 01:10.920 --> 01:14.950 attributes regarding the location of the property and different details. 01:16.050 --> 01:23.640 So your task here is to build a predictive model for predicting whether a property should be marked 01:23.640 --> 01:26.850 as junk on the basis of the listing details. 01:26.850 --> 01:31.890 And the different preliminary assessment is now here. 01:32.130 --> 01:40.620 You how you will be evaluating your model is on the basis of the U.S. score, which has to be more than 01:40.620 --> 01:41.930 zero point six five. 01:41.970 --> 01:44.700 What do you do for this particular project? 01:45.270 --> 01:47.550 So let's have a look at the data set. 01:47.580 --> 01:50.900 So here you can see this particular poll over just junk. 01:51.300 --> 01:53.360 This is the target column. 01:53.370 --> 01:59.490 So you need to classify these properties so that you get a value, either zero or one here. 02:00.000 --> 02:08.190 And here are different columns with different types of values, such as impedance style, price details, 02:08.190 --> 02:16.290 listing the material, the channel, the zip code, the insurance, the blood type architecture and 02:16.290 --> 02:18.740 different different information represented. 02:19.020 --> 02:23.870 So what you will have to do is, again, you can see there are a lot of categorical variables. 02:24.300 --> 02:32.160 So your main focus here would be looking for these variables into dummy variables and then to find out 02:32.160 --> 02:34.750 the variables which are actually important. 02:36.570 --> 02:47.310 So I hope you will be working on this particular project and would be so able to solve this very easily 02:47.310 --> 02:54.690 as this is not a very complex problem, but again, has a lot of tasks which you would have to perform 02:54.690 --> 02:57.150 so that you can achieve a good result. 02:57.870 --> 02:58.440 Thank you.