What-If Forecasting: Price Effects in Retail

Learn how to use TimeGPT to forecast sales scenarios with different pricing strategies.

TimeGPT makes it possible to forecast product demand in the retail sector and evaluate how different pricing scenarios might affect demand. Scenario analysis offers valuable insights for informed decision-making.

Forecast product demand using price as an exogenous variable

Evaluate different pricing scenarios

1. 1. Import required packages

   Import the packages needed for this tutorial and initialize your Nixtla client:

   Import Packages and Initialize NixtlaClient

   import pandas as pd
   import os
   
   from nixtla import NixtlaClient
   from datasetsforecast.m5 import M5
   

   Standard Endpoint

   If you are using Nixtla’s standard endpoint, simply provide your API key:

   Initialize NixtlaClient with Standard Endpoint

   nixtla_client = NixtlaClient(
       api_key='my_api_key_provided_by_nixtla'
   )
   

   Azure AI Endpoint

   If you have an Azure AI endpoint, configure the base_url argument accordingly:

   Initialize NixtlaClient with Azure AI Endpoint

   nixtla_client = NixtlaClient(
       base_url="your azure ai endpoint",
       api_key="your_api_key"
   )
   
2. 2. Load the M5 dataset

   We will use the M5 dataset, containing product sales data from 10 US retail stores. The data includes:

   DataFrame	Contents
   Y_df	Historical sales (y) for each product (unique_id) and date (ds).
   X_df	Additional information (exogenous variables) such as sell_price.

   For a full tutorial on incorporating exogenous variables with TimeGPT, please see the dedicated documentation.

   Load M5 Dataset

   Y_df, X_df, S_df = M5.load(directory=os.getcwd())
   Y_df.head(10)
   

   Because we want price-driven demand forecasts, we’ll focus on the sell_price column:

   Select Sell Price Column

   X_df = X_df[['unique_id', 'ds', 'sell_price']]
   X_df.head(10)
   
3. 3. Forecast demand using price as an exogenous variable

   In this example, we forecast for a single product (FOODS_1_129_) across all 10 stores. This product exhibits frequent price changes, making it ideal for modeling price effects on demand.

   Select Products for Forecasting

   products = [
       'FOODS_1_129_CA_1', 'FOODS_1_129_CA_2', 'FOODS_1_129_CA_3', 'FOODS_1_129_CA_4',
       'FOODS_1_129_TX_1', 'FOODS_1_129_TX_2', 'FOODS_1_129_TX_3',
       'FOODS_1_129_WI_1', 'FOODS_1_129_WI_2', 'FOODS_1_129_WI_3'
   ]
   
   Y_df_product = Y_df.query('unique_id in @products')
   X_df_product = X_df.query('unique_id in @products')
   

   Merge the sales (y) and price (sell_price) data into one DataFrame:

   Merge Sales and Price Data

   df = Y_df_product.merge(X_df_product)
   df.head(10)
   

   Check the historical demand and pricing trends:

   Plot Historical Demand

   nixtla_client.plot(df, unique_ids=products, max_insample_length=365)
   

   Plot Historical Prices

   nixtla_client.plot(df, unique_ids=products, target_col='sell_price')
   

   Now, split the data into: • Training data (df_train) • Future exogenous data (future_ex_vars_df)

   Split Data into Train and Future Exogenous

   future_ex_vars_df = df.drop(columns=['y']).query("ds >= '2016-05-23'")
   df_train = df.query("ds < '2016-05-23'")
   

   Generate forecasts using TimeGPT (28 days ahead):

   Generate Baseline Forecast

   timegpt_fcst_df = nixtla_client.forecast(
       df=df_train,
       X_df=future_ex_vars_df,
       h=28
   )
   timegpt_fcst_df.head()
   

   When using Azure AI endpoints, specify model="azureai" in the forecast call. Refer to the official tutorials for more details.

   Finally, visualize your baseline forecast:

   Plot Baseline Forecast

   nixtla_client.plot(
       df[['unique_id', 'ds', 'y']],
       timegpt_fcst_df,
       max_insample_length=56
   )
   
4. 4. 'What if?' forecasting: exploring price changes

   We’ll now explore ±5% price changes and their impact on demand. Adjust future prices, forecast demand, and compare to the baseline:

   Apply Price Scenarios for Forecasting

   price_change = 0.05
   
   future_ex_vars_df_plus = future_ex_vars_df.copy()
   future_ex_vars_df_plus["sell_price"] *= (1 + price_change)
   
   future_ex_vars_df_minus = future_ex_vars_df.copy()
   future_ex_vars_df_minus["sell_price"] *= (1 - price_change)
   
   timegpt_fcst_df_plus = nixtla_client.forecast(df_train, future_ex_vars_df_plus, h=28)
   timegpt_fcst_df_minus = nixtla_client.forecast(df_train, future_ex_vars_df_minus, h=28)
   

   Rename and combine the scenario forecasts:

   Rename and Combine Scenario Forecasts

   timegpt_fcst_df_plus.rename(
       columns={'TimeGPT': f'TimeGPT+{price_change*100:.0f}%'},
       inplace=True
   )
   
   timegpt_fcst_df_minus.rename(
       columns={'TimeGPT': f'TimeGPT-{price_change*100:.0f}%'},
       inplace=True
   )
   
   timegpt_fcst_df = pd.concat(
       [
           timegpt_fcst_df,
           timegpt_fcst_df_plus.iloc[:, -1],
           timegpt_fcst_df_minus.iloc[:, -1]
       ],
       axis=1
   )
   

   Visualize all three forecasts (baseline, +5%, and –5%):

   Plot Scenario Forecasts Comparison

   nixtla_client.plot(
       df[['unique_id', 'ds', 'y']],
       timegpt_fcst_df,
       max_insample_length=56
   )
   

   What is Price Elasticity?

   Price elasticity measures demand sensitivity to price changes. For more details, see this Wikipedia article.

   Important Considerations

   • Forecasting relies on historical patterns, which may not capture entirely new market conditions.

   • Include additional exogenous variables if you expect them to significantly impact sales.

   • If historical data capture major market shifts, explicitly model them for better accuracy.