Could ChatGPT get an MBA from Wharton?

Posted 2 years ago by Arshavir Blackwell

A ChatGPT MBA?

Christian Terwiesch of the Mack Institute for Innovation Management at the Wharton School asks: “Would Chat GPT3 Get a Wharton MBA?” He notes that the AI system is capable of performing basic operations management and process analysis questions. It often provides correct answers and excellent explanations. He notes that ChatGPT modifies answers in response to human hints, and even appears to learn, suggesting the importance of keeping a human as part of the generative process.

However, he also notes that it made mistakes in simple calculations, including at the level of 6th grade Math. It did not appear capable of handling more advanced process analysis questions. It required substantial adjustments before producing usable exam questions, in those cases where it was able to generate new questions.

Terwiesch writes that it would receive a B or B- grade on an exam.

Here are some examples of the questions he gave ChatGPT, how it answered, and his evaluation of that answer:

Question

The Circored process produces direct reduced iron in Latin America. The production process starts with a pile of iron ore fines. The ore is moved through seven process steps before it emerges as finished direct-reduced-iron briquettes. The steps and their capacities are as follows:
• Pre-Heater: 60 tons per hour
• Lock Hoppers: 55 tons per hour
• First reactor: this reactor holds up to 14 tons of iron and iron needs to spend 15 minutes in
the reactor
• Second reactor: this reactor holds up to 200 tons of iron and iron needs to spend 4 hours in
the reactor
• Flash heater: 62.5 tons per hour
• Discharge: 59 tons per hour
• Briquetting: three machines of 27.5 tons per hour each
Where in the process is the bottleneck and what is the overall process capacity? Justify your answer.

Answer

The bottleneck of the process is the second reactor, and the overall process capacity is 50 tons per hour. This is because the second reactor has the lowest capacity and the longest residence time for the iron ore among the seven process steps. The other steps have higher capacities, but they can only work at the rate of the second reactor, so the overall process capacity is limited to this rate. For example, even though the pre-heater has a capacity of 60 tons per hour and the flash heater has a capacity of 62.5 tons per hour, the iron can only be processed at a rate of 50 tons per hour in the second reactor, so the overall process capacity is limited to this rate.

Grade

A+. The answer is correct and well explained. The response clearly explains idea of the bottleneck as the rate limiting step and all the calculations are correct.

Question

World-Antique is a new venture under development by two graduates of a New England business school. The value proposition of the venture is simple: purchase antique paintings at yard sales and auctions and then sell them at quadruple the purchase price via a simple eCommerce site (i.e., a painting that is purchased for $100 would be sold at $400). Based on an analysis of similar retailers, the founders expect to turn their inventory 1.5 times per year. 

To achieve an annual revenue of $3,000,000, how much inventory expressed in $’s should the founders expect their operation to require?

Answer

To achieve an annual revenue of $3,000,000, the founders need to sell $3,000,000 / 4 = $750,000 worth of paintings per year.

Since they expect to turn their inventory 1.5 times per year, they need to have $750,000 / 1.5 = $500,000 worth of inventory at any given time.

Therefore, the founders should expect their operation to require $500,000 worth of inventory.

Grade

A-. Succinct and correct.

Question

Consider the processing plant of a large cranberry cooperative. The plant receives 1,500 barrels of cranberries each hour, 70% of which are wet-harvested berries and 30% are dry-harvested berries. At the plant, dry-harvested and wet-harvested berries are processed differently.

All berries are received at a central receiving station. The station has five docks where trucks unload the berries. It takes about 8 minutes to unload one truck. The average truck has about 75 barrels of berries on it.

After the receiving station, dry berries are moved to destoning. Wet berries do not have to be destoned. There are three machines at destoning, each of which can process 1500 barrels per hour.

Next comes dechaffing, a step that needs to be completed for both dry-harvested and wet-harvested berries. There are three dechaffing machines, each of which can process 1,500 barrels per hour.

After dechaffing, the wet-harvested berries move on to the dryer. The dryer can process 600 barrels per hour. Dry-harvested berries do not have to be processed at the dryer.

Finally, all berries need to move through the separator. The separator can handle 1,200 barrels per hour.

Where in the process is the bottleneck?

Answer

To determine the bottleneck in the cranberry processing plant, we need to identify the step in the process with the lowest capacity.

At the receiving station, there are 5 docks where trucks can be unloaded, and it takes about 8 minutes to unload one truck with an average of 75 barrels of berries. This means that the receiving station has a capacity of 5 docks x 8 minutes/dock x 75 barrels/minute = 300 barrels/hour.

At destoning, there are 3 machines that can each process 1,500 barrels per hour, for a total capacity of 1,500 barrels/hour x 3 machines = 4,500 barrels/hour.

At dechaffing, there are 3 machines that can each process 1,500 barrels per hour, for a total capacity of 1,500 barrels/hour x 3 machines = 4,500 barrels/hour.

At the dryer, the capacity is 600 barrels/hour.
At the separator, the capacity is 1,200 barrels/hour.

Since the dryer has the lowest capacity at 600 barrels/hour, it is the bottleneck in the process. This means that the dryer will be the step that determines the overall capacity of the plant. All other steps in the process will have capacity to spare, as they can handle more than 600 barrels per hour.

Grade

C. The capacity calculations at the receiving station sound plausible, but they are wrong. However, ChatGPT did not believe in its own calculation, as it correctly labeled the dryer as the bottleneck, despite it having a higher capacity of 600 barrels per hour. It also mistook the multi-product plant as a single product plant.

The lengthy paper provides a total of ten such question and answer pairs. The paper concludes with many recommendations, including that ChatGPT be used to improve the teaching process and that students should be permitted to use ChatGPT as a tool.

Author