Learn Applying Machine Learning to Operations | Optimizing Operations with Python

Machine learning is a powerful tool that can help you make smarter decisions in operations management by uncovering patterns in data and making predictions about the future. In operations, you might use machine learning for tasks such as predicting product demand, identifying anomalies in supply chain processes, forecasting inventory needs, or even optimizing staffing schedules. For example, if you want to predict how many units of a product you will sell next month, machine learning can help you analyze historical sales data and external factors to make an informed estimate. Similarly, you can use anomaly detection methods to spot unusual spikes or drops in production, which might indicate a problem that needs immediate attention.


              123456789101112131415161718192021
            
import pandas as pd
from sklearn.linear_model import LinearRegression

# Sample historical sales data
data = {
    "month": [1, 2, 3, 4, 5, 6],
    "sales": [200, 220, 250, 265, 300, 320]
}
df = pd.DataFrame(data)

# Prepare features (X) and target (y)
X = df[["month"]]
y = df["sales"]

# Create and train the model
model = LinearRegression()
model.fit(X, y)

# Print model coefficients
print("Intercept:", model.intercept_)
print("Slope:", model.coef_[0])

When you train a machine learning model, you provide it with historical data so it can learn the relationship between input variables (like time or promotions) and the outcome you care about (such as sales). The model uses this information to find patterns and generate a mathematical formula for making predictions. Once trained, you can use the model to predict future outcomes, which is especially valuable for planning and resource allocation. Interpreting the results involves looking at the model's coefficients to understand how each input affects the prediction. For operational decisions, this means you can estimate the impact of changes—like running a promotion or adjusting staffing—before taking action.


              1234567891011121314
            
import numpy as np

# Predict sales for the next two months
future_months = np.array([[7], [8]])
predicted_sales = model.predict(future_months)

print("Predicted sales for month 7:", int(predicted_sales[0]))
print("Predicted sales for month 8:", int(predicted_sales[1]))

# Example operational action
if predicted_sales[0] > 330:
    print("Trigger: Increase inventory for month 7.")
else:
    print("Trigger: Maintain current inventory levels for month 7.")

Everything was clear?

Thanks for your feedback!

Section 3. Chapter 6

Ask AI

Ask anything or try one of the suggested questions to begin our chat

Swipe to show menu


              123456789101112131415161718192021
            
import pandas as pd
from sklearn.linear_model import LinearRegression

# Sample historical sales data
data = {
    "month": [1, 2, 3, 4, 5, 6],
    "sales": [200, 220, 250, 265, 300, 320]
}
df = pd.DataFrame(data)

# Prepare features (X) and target (y)
X = df[["month"]]
y = df["sales"]

# Create and train the model
model = LinearRegression()
model.fit(X, y)

# Print model coefficients
print("Intercept:", model.intercept_)
print("Slope:", model.coef_[0])


              1234567891011121314
            
import numpy as np

# Predict sales for the next two months
future_months = np.array([[7], [8]])
predicted_sales = model.predict(future_months)

print("Predicted sales for month 7:", int(predicted_sales[0]))
print("Predicted sales for month 8:", int(predicted_sales[1]))

# Example operational action
if predicted_sales[0] > 330:
    print("Trigger: Increase inventory for month 7.")
else:
    print("Trigger: Maintain current inventory levels for month 7.")

Everything was clear?

Thanks for your feedback!

Section 3. Chapter 6

Applying Machine Learning to Operations

1. What is the benefit of using machine learning in operations management?

2. Which scikit-learn class is used for linear regression?

3. How can predictions from a model inform operational decisions?

Applying Machine Learning to Operations

1. What is the benefit of using machine learning in operations management?

2. Which scikit-learn class is used for linear regression?

3. How can predictions from a model inform operational decisions?