Second review

EVALUATION REPORT — ATTEMPT 1 — REVISION NEEDED

Overall Evaluator Comments

EVALUATOR COMMENTS

Your work here identifies a business question for the scenario and understands why the decision tree is a good path forward. Your analysis shows your understanding of possible limitations for the data element and the decision tree. Please see the comments in the rubric for more information about the aspects that require revision.

A. Business Problem Description

Competent

Competent The business question is accurately described, is relevant to the scenario, and is appropriate for decision tree analysis.

· There are no comments for this aspect.

B. Relevant Data

Competent

Competent The relevant data values are accurately identified for the decision tree analysis, including each of the given elements.

· There are no comments for this aspect.

C1. Decision Tree Diagram

Approaching Competence

Approaching Competence, the decision tree diagram provided does not contain 1 or more of the given elements, or the decision tree diagram contains 1 or more inaccuracies.

EVALUATOR COMMENTS: ATTEMPT 1

The work includes a decision tree. However, 2 of the payoff values are incorrect, and one of the three expected values is incorrect.

C2. Analysis Technique Justification

Competent

Competent The justification of decision tree analysis logically explains why it is the appropriate analysis technique and is supported with relevant details from the scenario.

· There are no comments for this aspect.

D1. Probabilities and Demand

Approaching Competence

Approaching Competence, the explanation does not logically address both the role of probabilities and the role of demand for 1 or more of the branches of the decision tree analysis.

EVALUATOR COMMENTS: ATTEMPT 1

The work describes decision tree values. However, the role probabilities and demands play is not logically addressed.

D2. Expected Values

Approaching Competence

Approaching Competence, the explanation does not logically and accurately address 1 or more steps required to determine the value of 1 or more nodes based on payoffs.

EVALUATOR COMMENTS: ATTEMPT 1

The work describes expected values. However, not all steps in the calculation process are identified.

D3. Limitations

Competent

Competent The discussion logically addresses 1 limitation of the data elements and 1 limitation of the decision tree analysis.

· There are no comments for this aspect.

E. Recommend Course of Action

Approaching Competence

Approaching Competence, the recommended course of action is not logically supported by the results of the decision tree analysis or does not appropriately address the business question from part A.

EVALUATOR COMMENTS: ATTEMPT 1

The recommendation appears to be correct; however, the inaccuracies of the decision tree diagram may impact the recommended course of action.

F. Sources

Competent

Competent The submission includes in-text citations for sources that are properly quoted, paraphrased, or summarized and a reference list that accurately identifies the author, date, title, and source location as available.

· There are no comments for this aspect.

G. Professional Communication

Competent

Competent Content reflects attention to detail, is organized, and focuses on the main ideas as prescribed in the task or chosen by the candidate. Terminology is pertinent, is used correctly, and effectively conveys the intended meaning. Mechanics, usage, and grammar promote accurate interpretation and understanding.

· There are no comments for this aspect.

Decision Tree Analysis

Data- Driven Decision Making

Rolanda Martin

Western Governors University

Mr. Tony Pineda

C207 Data – Driven Decision Making

May 15, 2024

Decision Tree Analysis

Market Research Report

Today's pharmaceutical world is changing. As Chief Operating Officer of Major Pharmaceutical Company (MPC), I deliver a complete market research report to help formulate MPC's drug line development strategy. Our focus revolves around two key alternatives: developing a new drug (exhibition) or modifying an existing drug (exploitation of new applications). Market conditions are decisive, and our analysis examines both favorable and unfavorable cases. In a real ideal market, our new drug line has a 69% probability of success with a sale of 4133 units per month, and the old drugs have already achieved a probability of 69% (DiMasi, 2020). If the status quo is maintained, there is a 77% probability of success with an order for 657 units.

Meanwhile, in an undesirable market, the demand for a new drug line is 1355 units, the existing drug line is at 1911 units, and simply maintaining the current strategy means a demand of 258. The new drug is $0.65 per unit, the existing drug has new uses but the same price, $0.77, and the current drug is at its present price of $0.87 per unit. In this report, decision tree analysis is used to suggest a set of actions with values (probabilities and payoffs) estimated under different conditions. Limitations identified include uncertainties regarding data and potential shortcomings of the decision tree analysis method. These recommendations will give MPC a clear direction of how to go based on our business and market conditions.

Business Question and Applied Decision Tree Analysis

The central business question derived from the scenario is: Is there a single decision alternative offering the highest expected financial outcome today, given current market research? Should it be new drug development, expanding the established drug line or continuing with existing levels of production and sales? A decision tree analysis was used to answer that question. For each alternative, the probabilities, payoffs and profits under favorable and unfavorable market conditions were systematically worked out. These Expected Monetary Values (EMVs) calculated for each decision alternative form a strategic basis for recommending the most financially feasible course of action (Gupta et al., 2017).

Relevant Data Values Required for Decision Tree Analysis

Relevant data provided in the scenario included every alternative, the probability of a favorable or unfavorable market. For every alternative, there was the expected demand in a favorable and unfavorable market, as well as the profit per unit. Having this information, it is now easy to calculate the EMV.

Favorable Market
Alternative	Probability	Demand	Profits	Payoff
Develop a new drug line	69	4133	0.65	2686.45
Expand existing drug line	61	5577	0.77	4294.29
Continue existing line	77	657	0.87	597.69
Unfavorable Market
Develop a new drug line	31	1355	0.65	880.75
Expand existing drug line	39	1911	0.77	1471.47
Continue existing line	23	258	0.87	224.46

Decision Tree

The decision tree analysis tool is used to compare several options and different decisions, with the aim of making a judgment on what course to take based on the results of comparing all possible alternatives. For this case, MPC should consider three alternative options and take the best one. It should consider either developing a new drug line, expanding the existing drug line or continuing with the existing line. Using this kind of analysis tool, it is possible to compare all these options and their respective outcomes. Based on this comparison, we have a chance to choose the option that has the highest positive answer.

Implications of Decision Tree Analysis

Develop a New Drug Line

Probabilities and Demand - Under a probability of 69% favorable market conditions, demand for the new drug line is estimated to be 4133 units per month. On the other side, a 31% vesting probability for an unfavorable market condition lowers demand to 1355 units.

Expected Value Determination - The decision tree analysis yields an expected monetary value (EMV) of $2124.33 for developing a new drug line. Thus, given the uncertainties of market conditions, this choice works out to a positive expected financial bottom line.

Expand Existing Drug Line

Probabilities and Demand - According to the expectation of a favorable market (61% probability), demand for the existing drug line expansion in one month is estimated at 5577 units. If the market turns unfavorable (about a 39% chance), demand drops to 191 units.

Expected Value Determination - If expanding the existing drug line is an option, then EMV is $3194.04. Based on decision tree analysis, compared with other options, this alternative has a higher expected financial outcome.

Continue Existing Line

Probabilities and Demand - When there is a favorable market, the probability of success associated with continuing the drug line is 77%. In such cases, demand will reach 657 units. For an unfavorable market (23% probability), demand drops to 258 units.

Expected Value Determination - The EMV for continuing the current drug line is $512.56. This option has a lower expected financial outcome than the other choices, but it is stable and low-risk.

Limitations

Though it is effective, decision tree analysis has its limitations. One problem is that the accuracy of data elements depends on individual interpretation. Where probabilities, payoffs, or profits are based on unreliable or outdated information, the analysis could produce misleading results. Moreover, decision tree analysis relies on the assumption that events are independent of one another. However, in real-life business problems, this is only sometimes the case. There are also political, social, short-term, and long-term consequences of making business decisions. The decision tree analysis only looks at one-dimensional profit potential (Pauker & Kassirer, 2019; Rennane et al., 2021).

Recommendations

The decision to expand the existing drug line is recommended since it gives the largest EMV of $3194.04. This decision reflects Major Pharmaceutical Company's desire to strive for maximum profit while attaining a balanced risk-return ratio (Charbuty & Abdulazeez, 2021). The expansion strategy seeks to take advantage of market opportunities and ride on proven success. There is also an option for developing a new drug line that has the second-highest EMV but has a lower profitability. The recommendation intends to direct MPC institutionally toward optimal decision-making in a rapidly changing pharmaceutical market.

References

Charbuty, B., & Abdulazeez, A. (2021). Classification based on decision tree algorithm for machine learning.  Journal of Applied Science and Technology Trends,  2(01), 20-28.

DiMasi, J. A. (2020). Research and development costs of new drugs.  JAMA,  324(5), 517-517.

Gupta, B., Rawat, A., Jain, A., Arora, A., & Dhami, N. (2017). Analysis of various decision tree algorithms for classification in data mining.  International Journal of Computer Applications,  163(8), 15-19.

Pauker, S. G., & Kassirer, J. P. (2019). Decision analysis.  Medical uses of statistics, 159-179.

Rennane, S., Baker, L., & Mulcahy, A. (2021). Estimating the cost of industry investment in drug research and development: a review of methods and results.  INQUIRY: The Journal of Health Care Organization, Provision, and Financing,  58, 00469580211059731.