Managerial Economics/Development of managerial economics

Data Science

Data science is an interdisciplinary field that combines tools from statistics, computer science, machine learning and various social sciences to extract insights from data.

Big Data

The rise of big data is due to digital technologies advancement, leading to the creation and accumulation of massive amounts of unstructured data. It becomes cheap, while data scientists, which are complements, become expensive.

What makes data big

Volume:

• Currently, every person generates about 100+ GB of data each day.

Velocity:

• Data is collected in real-time.

Variety:

• Multiple data sources: messages, tweets, images and video posted to social networks; readings from sensors; GPS signals from cell phones, security camera recordings, and more.

• High dimensionality.

What makes a data science manager

A data science manager is usually responsible for:

• recruiting data engineers and data scientists;

• identifying problems that need to be solved,

• putting the right people on the right problem;

• setting goals and priorities;

• managing the data science process.

Ideally, data science managers should be generalists who have knowledge of the software and hardware being used, have good communication skills and domain knowledge.

Machine Learning

Machine learning (ML) algorithms build a mathematical model based on training data, to make predictions on new data.

ML is used:

- to predict a future that looks mostly like the past;

- for pattern recognition;

- for decision making.

Corelation = Causation

Data scientists are often only interested in prediction, not causality e.g. if you liked the movie Frozen, you might like Madagascar.

Occasionally, correlation is all that is needed. Causation may not be required.

Machine Learning Paradigms

Machine learning (ML) is a method of data analysis base on training data to identify patterns and make predictions on new data.

1. Unsupervised learning

- Uses training data that contains the inputs and but not the outputs to build an algorithm to uncover patterns in the data.

- E.g. cluster groups with similar purchasing habits for targeting ads.

2. Supervised learning

- Uses training data that contains both the inputs and the desired outputs to build an algorithm to predict the output when it is not observed.

- E.g. classification algorithms (spam/not spam)

3. Reinforcement Learning

- Learn how to take actions to maximize cumulative reward.

- Trade-off between exploration and exploitation (of current knowledge)

Computation

A data scientist needs to be able write code. The most popular programming languages used by data scientists are:

1. R

- Rich ecosystem, open-source library of packages

2. Python

- Better suited for machine learning at a large-scale.

- Easier to maintain and more robust codes than R

Data Extraction Tools

• SQL: Structured Query Language

Data Visualization

Data visualization is the graphical representation of information and data. ITs purpose is to:

• To provide an accessible way to see and understand trends, outliers, and patterns in data.

• Uses visual elements like charts, graphs, and maps, animations.

• Tools: Tableau, PowerBI, Qlikview, Chart Studio, FusionCharts, Highcharts, Datawrapper, Sisense, Chart.js, D3.js….

Data Visualization Principles

1. Show the data

2. Induce the viewer to think about the substance rather than about methodology, graphic design, the technology of graphic production or something else.

3. Avoid distorting what the data has to say.

4. Present many numbers in a small space.

5. Make large data sets coherent.

6. Encourage the eye to compare different pieces of data.

7. Reveal the data at several levels of detail, from a broad overview to the fine structure.

8. Serve a reasonably clear purpose: description, exploration, tabulation or decoration.

9. Be closely integrated with the statistical and verbal descriptions of a data set.

Reproducibility of Data Science Reports

Reproducibility occurs when an independent researcher is able to replicate the analysis and achieve the same results. This ensures:

1. that finding are verifiable;

2. an increase in the robustness of findings (findings have stronger credentials);

3. the providence of building blocks for others to expand on reported research.

Practices

1. The research report should be accompanied with the original data.

2. The data generating process should be explained replicate the data generation process (e.g. experiment).

3. Data analysis should be fully automated and the code to produce the results should be made publicly available.

4. The analysis code should be written in a clear and concise way.

Artificial Intelligence

Artificial Intelligence Combining multiple ML algorithms together to solve complex problems.

1. Define the domain structure

- Conduct experiments, build data management systems.

- Possible to simulate data for ML in games like Go.

Break a complex problem into composite tasks that can be solved with ML. So far very successful in well-defined structured games (Chess, Go, Pacman). Domain expertise (e.g. economic theory) is valuable in business applications

2. Generate the necessary data

3. Build ML algorithms for each task and combine the information to make decisions

Development

The development of managerial economics is attributed to the close relationship that exists between management and economics (Brickley, Smith, & Zimmerman, 2015). For example, management requires a great deal of economic analysis in the carrying out of evaluations aimed at establishing the demand, cost, competition, and profit associated with certain goods and services (Brickley et al., 2015). On the other hand, management plays a significant role in guaranteeing that all challenges that may arise, particularly in the handling of employees are adequately addressed (Brickley et al., 2015). Thus, the combination of these two aspects of business results in managerial economics, which comprises of managerial theories and economic theories aimed at guaranteeing the development of a sustainable business environment (Brickley et al., 2015). The concept behind managerial economics is best elaborated by Spencer and Siegelman, who defined it as “the integration of economic theory with business practice for the purpose of facilitating decision making and planning by management” (Brickley et al., 2015).

Objectives

Managerial economics meets its objectives by integrating diverse economic aspects such as microeconomics and macroeconomics. Microeconomic is designed around studying the actions firms and individual consumers with the aim of understanding what influences certain business patterns at the regional level (Brickley et al., 2015). Macroeconomics is centred on analysing the structure, performance, and the behaviour of the economy as a whole (Brickley et al., 2015). While managerial economics incorporates the use of microeconomics in the implementation of certain theories and techniques aimed at improving management decisions, it is important to note that the scope of microeconomics is limited compared to macroeconomics (Brickley et al., 2015). On the other hand, macroeconomics analyses aggregate indicators such as the unemployment rate and the GDP to have a vast understanding of the factors that are influencing the general economy (Brickley et al., 2015).

Use of Quantitative Methods

The incorporation of microeconomics in managerial economics is influenced by the fact that they both advocate the need to utilise quantitative methods in evaluating economic data. By utilising quantitative analysing methods, it becomes possible to warrant that the human and financial resources required to manage a particular business effectively are allocated efficiently (Froeb, McCann, & Ward, 2015). On the other hand, the use of macroeconomics in managerial economics is based on the impact it has in providing a wider scope on the overall condition of the economy. The information acquired using macroeconomics is what governments utilise in the establishment of policies aimed at enhancing an economy (Froeb et al., 2015).

Primary Function

Even though managerial economics is comprised of numerous functions, it's primary function is effective decision-making. This is attained by taking courses of actions that warrant that every challenge is addressed using the most suitable option derived from two or more alternatives (Froeb et al., 2015). The need to take the best course of action is influenced by the fact that in spite of the numerous roles an organisation plays, its responsibility to its shareholders is that the available resources are utilised in the best way post to warrant profitability (Froeb et al., 2015). While the use of microeconomics and macroeconomics have been noted to have a critical role in shaping the role of managerial economics, it is important to note that it is a continuous process since it has not met its maximum potential (Froeb et al., 2015). In addition to micro and macroeconomics, capital management, profit management, and demand analysis and forecasting are also considered to be covered under the scope of managerial economics (Froeb et al., 2015). Based on the evaluation provided, it is inevitable to note the significant role managerial economics has in warranting managerial challenges are handled in the manner possible using diverse economic concepts and decision science techniques.

References

Brickley, J., Smith, C., & Zimmerman, J. (2015). Managerial economics and organizational architecture. New York: McGraw-Hill Education.

Froeb, L. M., McCann, B. T., & Ward, M. R. (2015). Managerial economics. Boston, Massachusetts: Cengage learning.