The dataset includes 30+ features such as CPU, GPU, RAM, storage, display type, and other specifications that influence device pricing. The target variable is price, and that is what you want to predict.

Note: I have cleaned the dataset to remove NaNs and other anomalies. If you notice any other anomalies within the dataset, make sure to publish your findings in the next competition so I can do my preprocessing better.

The train dataset is `computer_prices_all.csv` and the test dataset is `computer_prices_test.csv`
# 📊 Dataset Structure 

Rows: 100,000 (Exactly 100,000! Such a nice number!)

Columns: 33

Target: price

Feature Groups

Device Information: device_type, brand, model, release_year, form_factor, os

Note: the model column isn't  actually a real model - I concatenated different words together about the computer. I'm not sure if the column provides any additional information, but I left it there just in case someone found any signal from the feature. 

Also, there are always 3 letters/numbers at the end of the model name. I don't think it means anything, but sometimes the 3 letters were scraped (I am not sure from where) and other times it didn't so I just generated 3 letters/numbers at the end for all because it looked better 🥲

CPU Specs: cpu_brand, cpu_model, cpu_tier, cpu_cores, cpu_threads, cpu_base_ghz, cpu_boost_ghz

GPU Specs: gpu_brand, gpu_model, gpu_tier, vram_gb

Memory & Storage: ram_gb, storage_type, storage_gb, storage_drive_count

Display: display_type (LED, OLED, Mini-LED, QLED, IPS, VA), display_size_in, resolution, refresh_hz

Power & Form Factor: battery_wh, charger_watts, psu_watts

Connectivity: wifi, bluetooth

Other: weight_kg, warranty_months

Target: price