Learn practical skills, build real-world projects, and advance your career

Bulldozer Auction Sales Price Prediction

final.jpg

Hey there, we were assigned with a new problem.

We were asked to predict the sale price of a particular piece of heavy equiment at auction based on it's usage, equipment type, and configuaration. The data is sourced from auction result postings and includes information on usage and equipment configurations(Source).

So, How do we tackle?

They are asking us to predict the auction Salesprice of the product based on the data we were given.

Okay, so we will be following the given steps to get to our solution:-

  1. Download a real-world dataset and analyse it.
  2. Explore and visualise the data.
  3. Cleaning and feature engineering of the data.
  4. Train the First ML model on the dataset.
  5. Tune hyperperameters and regularization.
  6. Doing the 4 and 5 steps for the second and thrid ML model.
  7. Making predictions and submitting the predictions.

  1. Saving the model.
  2. Summary and references.

Now before starting, let's download the essential libraries and commit to jovian and then let's get started.

!pip install numpy pandas matplotlib seaborn --quiet #these libraries are for cleaning and visualisation.
!pip install jovian opendatasets xgboost graphviz scikit-learn --upgrade --quiet
#The above are model related libraries(mostly except opendatasets and jovian)
|████████████████████████████████| 192.9 MB 66 kB/s |████████████████████████████████| 46 kB 2.5 MB/s
# Execute this to save new versions of the notebook
jovian.commit(project="bosch-production-line-performance")

Download a real-world dataset and analyse it.