Get startedGet started for free

Probabilities in Decision Models

1. Probabilities in Decision Models

In this video we'll learn to apply probabilities in decision models.

2. Probabilistic Models

Probabilistic Models support decision-making by providing a structured approach to handle uncertainties. By using probabilities in decision models we quantify uncertainties by assigning values between 0 and 1 to express the likelihood of different outcomes.

3. Probabilities and uncertainties

We calculate probability by dividing the number of favorable outcomes by the number of possible outcomes. This chart illustrates how probabilities can quantify uncertainties. It ranges from 0% being "impossible" and 100% being "certain". For example, a probability between 0 and 20% translate to a "very unlikely" chance. Inversely, a probability between 80 and 100% percent, falls in the "very likely" chance. Let`s look closer in one example.

4. Probabilities in a coin toss

In a standard coin with Head and Tail on each side, let`s find the likelihood of the coin landing on Head twice consecutively. Given it's a regular coin, the first flip has two possibilities: Head our Tail. Each of these outcomes has a 50% chance.

5. Probabilities in a coin toss

In the second flip, we see that each previous outcome can generate two other outcomes with a 50% chance each. With this model we can define the possible combinations and their probabilities.

6. Probabilities in a coin toss

We now have four possible outcomes given the two consecutive flips. Each outcome has a 25% probability.

7. Probabilities in a coin toss

Specifying the "two consecutive heads combination", we realize that the chance of that happening is 25%. Unlikely.

8. Probabilities in a coin toss

What about landing on heads first and tails second? Once again, this specific combination lead us to a 25% probability. Unlikely.

9. Probabilities in a coin toss

How about landing on tails at least once in two flips? This result is reached by three out of four outcomes. So this chance is 75%. Very likely.

10. Building a Probabilistic Decision Model

Now in this Probabilistic Decision Model, a retail company is deciding where to launch the next marketing campaign: In Social Media, or in the Newspaper Ads.

11. Building a Probabilistic Decision Model

Advertising in Social Media costs $100. This cost in the Newspaper Ads. is $90.

12. Building a Probabilistic Decision Model

Each option has two main outcomes: Success, or Fail.

13. Building a Probabilistic Decision Model

In both options, the probability of each possible outcome is 50%.

14. Building a Probabilistic Decision Model

The team calculated the profit and loss values of each possible outcome. A successful social media campaign for example, generates a $1000 profit.

15. Building a Probabilistic Decision Model

Let's update these profits and losses values including the costs of each campaign.

16. Building a Probabilistic Decision Model

And this is the final payoff of each outcome.

17. Evaluating expected value

The final model enable us to calculate the expected value for each option. It is the probability of success times the potential profit, plus, the probability of failure times potential loss.

18. Evaluating expected value

Consequently, the expected value of a Social Media campaign is $300.

19. Evaluating expected value

Analogous, the expected value of a Newspaper ads campaign is $335.

20. Evaluating expected value

Considering theses parameters a Newspaper ads campaign would be a better choice in relation to Social Media given its higher Expected Value.

21. Let's practice!

Now, let's practice this a little bit!

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.