What will happen?
1. What will happen?
Welcome. In this video, we will deep dive into business questions than can be answered using predictive analytics.2. Understanding what will happen
Unlike descriptive and diagnostic analytics, which are concerned with past and current events, predictive analytics is focused on using past data to make predictions about what is likely to happen in the future. Predictive analytics is a valuable tool for businesses across a wide range of industries. Let’s see some applications.3. Retail industry example
Retailers use predictive analytics to find how much of a particular product they should order to meet customer demand and minimize inventory costs. The analytical question is the following: What is the predicted customer demand for product x based on various factors such as historical sales volumes, seasonal factors, and the customer demographic? To answer this question, the analytics team can use historical data and relevant variables to train a time series forecasting model using machine learning algorithms. Once the model is trained and validated, the retailer can use it to forecast demand for the product over a given time period. This information can be used to make more informed decisions about how much of the product to order and when to order it, helping to minimize inventory costs and prevent stockouts.4. Insurance industry example
In the insurance industry, companies can use predictive analytics to identify fraudulent claims and mitigate the risk of fraudulent payouts. The analytical question, in this case, would be: What is the likelihood of a claim being fraudulent based on various variables from historical claim data? The variables could include the claimant's age, location, occupation, and claim details such as the type of claim and amount claimed. The analytics team can use a classification prediction algorithm to develop a model to predict the likelihood of fraud. By proactively identifying and preventing fraudulent claims, the insurance company can improve its profitability and protect its reputation.5. Healthcare industry example
In the healthcare industry, a business question can be, “How can we improve patient outcomes by identifying which patients are at risk for certain health conditions?” The analytical question will be: “Can we predict which patients are at risk for certain health conditions based on relevant variables?”. The variables, in this case, can be electronic medical records, lab results, clinical notes, and other patient data. Due to the unstructured and qualitative nature of the data, the analytics team may need to use machine learning-based text predictive modeling to analyze patient data and identify patterns and trends that may be indicative of certain health conditions. The model can identify symptoms, diagnoses, and treatment plans associated with specific health conditions. This information can be used to develop targeted prevention and treatment strategies for at-risk patients.6. Scenario in the finance industry (1/2)
Great! Now let’s deep dive further with a scenario. In finance, banks and financial institutions use predictive analytics to identify credit risk, detect fraud, and predict market trends. Let’s suppose that we have the business question, “How can we identify which loan applications are most likely to result in default?”. Although we can use descriptive and diagnostic analytics to understand which loan applications resulted in default in the past, the question is focusing on future applications. The analytical question is “Can we predict the likelihood of a loan application resulting in default based on various variables in the application?”. The variables, in this case, can be the applicant information such as. income, employment status, credit score, as well as the loan details such as the amount, term, and interest rate.7. Scenario in the finance industry (2/2)
The analytics team can use a classification prediction algorithm such as logistic regression using these variables. The model can be trained on a subset of the historical data, and then tested on a separate subset to ensure accuracy. Once the model is validated, it can be applied to new loan applications to predict the likelihood of default. By identifying high-risk applications, the bank can take steps to mitigate its risk of default and improve overall portfolio performance.8. Let's practice!
Great! Now, let’s check your understanding!Create Your Free Account
or
By continuing, you accept our Terms of Use, our Privacy Policy and that your data is stored in the USA.