Chat with us, powered by LiveChat ALY6100 Week 4 Data Driven Decision Making & Regression Method Paper | acewriters
+1(978)310-4246 credencewriters@gmail.com
  

(1,2) Email-essay + slideThis assignment builds off of Weeks 1, 2, and possibly 3 assignments. You are now at the decision point, and you know what Netflix, Netflix Prize Teams, or Salesforce decided in this case. This is the assignment where you make an argument for that decision. (Or you can make your own recommendation, if you prefer.) You can base this email-essay off of the Netflix or Salesforce cases, independent of what you wrote your earlier week’s assignments about.(1) Email-essay scenario: The data has been collected and analyzed. Time has come to make a decision and a plan based on the results of the analysis. As team lead for this project, your boss (or team) believes you have unique insights into the topic and wants your recommendation(s). What do you believe the company (or team) should do? What evidence* supports your recommendation(s)?Remember: You already know what Netflix/Netflix Prize Teams/Salesforce did in this decision making process. Specify:Summary of what you and the data analysis team learned in the analysis process*. What are the key findings? (Qualitatively, no numbers necessary.)At this point in the process, what is the desired outcome from this project? Include quantified goal or goals.What are the decision options?Specific recommendation, including enough information for another team to take over. You can say that you’re going to pass on data or code too. (e.g. in the Salesforce case, HR might take charge of the execution, but you can say you’ll give them the data about who needs to be paid more, you don’t need to give specific numbers)* Use the evidence from the case study and other research you may have done. Remember you have access to the Factiva database of articles from business publications including the Wall Street Journal. If there’s information you can’t find, feel free to things up, as long as the made up information is reasonable. Audience: Write your recommendations in the form of an email to your boss. Keep in mind they may forward the email their superiors. Requirements:Use in line citations where appropriateInclude a reference list/bibliographyMinimum 300 words(3) Short answerQuestions: (answer both) What leadership skills are relevant to your future work as a data scientist/analyst during data-driven decision making? Why? Reference the book and this week’s Lynda.com videos. Feel free to include any relevant examples from academic or professional experiences.Assuming the recommendation you made in the Email-Essay is followed, what uncertainty exists about the results or outcome?Thinking about this now will inform next week’s Email-Essay.RequirementsUse in line citations where appropriateInclude a reference list/bibliographyMinimum 300 wordsmaterials :https://www.lynda.com/Business-Skills-tutorials/Welcome/186697/373494-4.html
aly_6100_week_4_assignment_email.pdf

email_essay_3.docx

email.docx

email.docx

Unformatted Attachment Preview

Anita Lok
ALY 6100, Data-Driven Decision Making
Week 4 Assignment: Recommendation
——————————————————————————————————————–From: lok.ani@huskey.neu.edu
To: c.moore-kochlacs@northeastern.edu
Subject: Project Oxygen: Recommendation
Caroline,
Over the last two weeks, the data science team analyzed quantitative data from exit interviews,
employee surveys and performance reviews and conducted qualitative manager interviews. We
would like to share the key findings and provide you with a go-forward recommendation.
Key Findings:
Based on this information we proved managers do matter and that employee satisfaction and
retention correlated with manager quality and performance. We identified eight key behaviors
demonstrated by effective managers (Garvin, 2013):
1. Is a good coach
2. Empowers the team and does not micromanage
3. Expresses interest and concern for team members’ success and personal well-being
4. Is productive and results-oriented
5. Is a good communicator
6. Helps with career development
7. Has a clear vision and strategy
8. Has key technical skills
Recommendation:
Now that we have identified key behaviors of effective managers, it will be important to help
managers adopt these best practices by implementing the following three tools (Garvin, 2013).
Our first recommendation is to develop a hands-on training program for these managers to learn
about these behaviors and give a forum for managers to share best practices and suggestions with
one another.
The second recommendation is to build and implement an optional, confidential employee
survey using a five-point scale to evaluate their managers performance on these key behaviors.
Managers will be given a report of their numerical scores and links to more information about
best practices and suggested actions to improve. It is important to create this upward feedback
approach so that managers can use the information to continuously improve.
It critical that these decisions are clearly communicated by the leadership team to the
organization. It will be imperative that employees and managers see the technical results and be
able to see how this ties back to the business strategy (Bartlett, 2013 p. 141). As these new tools
are implemented, it will also be important to measure the results by aggregating employee survey
results and ask, are employees more satisfied and are managers improving on these key
behaviors? We would recommend gathering data over the next 12 months and seeing if there has
been significant progress made or if adjustments are needed.
Please let me know if you have any questions.
Thank you,
Anita Lok
References
Bartlett, R. (2013). A practitioner’s guide to business analytics: Using data analysis tools to
improve your organizations decision making and strategy. New York: McGraw-Hill.
Garvin, D. A. (2013, December). How Google Sold Its Engineers on Management. Retrieved
July 14, 2018, from https://hbr.org/2013/12/how-google-sold-its-engineers-on-management
Email Essay
One of the best data analytic technique to employ is the regression method. This is a very
powerful statistical method which provides the user with a room to make comparisons of
different variables. This method can be able to measure several types of data which include the
impact of an independent variable on a dependent one. From such an analysis, the user is in a
position to have detailed insight. From this, informed choices can be made to help in the
improvement of the quality of goods and services.
By using this method, you will be in a position to identify the variables which have a
significant impact on your projects or any topic of interest. With knowledge on the factors that
matter most, what is next apart from implementing them to enhance success? This is what every
person would like to know in an organization. The factors that matter list can be ignored or be
given minimum priority. This is the value of this method: enhancing productivity by helping one
identify the factors to eliminate through comparison.
To use this method, you will need to identify a comprehensive dataset which can be
obtained by addressing all the independent variables of interest. Then, bring in the dependent
variables that affect the independent variable for comparison of their significance. Using this
method is of great value since the impact of the different variables are determined and action
taken on time to eliminate the weaknesses. Despite its significance, this data technique has
different disadvantages which are based on the nature of the regression. For instance, for linear
regression, the assumption is that there must be a straight-line relationship. This is something
which does not hold for all relationships. Sometimes, one variable may assume a straight line
while the other one takes a curve. Good examples are age and finance. At the early life stages,
DATA ANALYSIS
we make more money; however, as we grow old, we retire and spend what we had contributing
to its decline.
1
DATA ANALYSIS
2
References
Controlling machine-learning algorithms and their biases. (n.d.). Retrieved from
https://www.mckinsey.com/business-functions/risk/our-insights/controlling-machinelearning-algorithms-and-their-biases
From yuan.yez@huskey.ney.edu
Subject: Reducing Errors for Efficiency
First Two Weeks’ Plan
With the increased need to get the attention of a diverse global audience for Netflix
movies and other content, the firm needs to work on increasing efficiency. This can only be
achieved by writing down a well-structured plan. The plan will consist of several elements which
include the strategies, datasets needed, and the time required for each action. The first steps will
entail identification of data sets first. The next two will be the implementation of the data set and
evaluation.
Step 1: Data Set Identification
The data set provides the baseline for the operation of this plan. The dataset needed is the
full MovieLens Dataset. This dataset consists of the movies released before 2017 July. Cast,
budget, posters, countries, crew, vote averages, language, and vote counts are the data points of
this set. These data points make the set a crucial one in the plan. They contain the information
needed to know the rating of the site when it comes to movie distribution. With such
information, accuracy can be achieved. This data set responds to all the business questions; for
instance, the different data points will tell the incidences from the previous years and solutions
be formed based on the research (Unwin, Hofmann & Theus, 2016). By identifying the crucial
point in the dataset, the team can new ways of improving efficiency. Nevertheless, by providing
the information on budget, the data team can identify several technologies to help in mitigating
the problem. This will solve the question regarding the exposure to the technologies (Amatriain
& Basilico, 2012). The sales data set is what the organization has at the moment internally. From
this data set, the organization is able to calculate the number of clients from the income
collected. This cannot be the only reliable data set since it limits things such as user opinions.
Thus, ratings will have some inaccuracies. This means that the sole and most useful data set for
Netflix at the moment is MovieLens since it has several subsets which will give more
information. The more the information available, the more accurate the data generated.
Step 2: Implementation
➢ Use the data set to improve efficiency.
➢ Formulation of solutions
Step 3: Evaluation
➢ Check id the implemented dataset is working as required.
➢ Find the changes it brings to the organization.
Sincerely
Allen
References
Amatriain. X., & Basilico. J. (2012, April 06). Netflix Recommendations: Beyond the 5 stars
(Part 1). Retrieved from https://medium.com/netflix-techblog/netflix-recommendationsbeyond-the-5-stars-part-1-55838468f429
Amatriain. X., & Basilico. J. (2012, April 06). Netflix Recommendations: Beyond the 5 stars
(Part 2). Retrieved from https://medium.com/netflix-techblog/netflix-recommendationsbeyond-the-5-stars-part-2-d9b96aa399f5
Unwin, A., Hofmann, H., & Theus, M. (2016). Graphics of Large Datasets: Visualizing a
Million.
2. 6 选一,允许团队做出艰难的抉择并且给出资源,允许犯错
3. 企业文化当中那些最重要的。
Hi,
First of all, we should understand what the meaning of data governance is. By the research and
the course material. We know that data governance is the overall management of the
availability, usability, security and integrity of data used in company. Then we look at the
picture about the data governance framework. We find the framework encompasses:
1. Corporate drivers – an understanding of what is causing the organization to manage and
monitor data more effectively. 2. Data governance strategies – the objectives, principles and
groups for a new (or newly aligned) data governance program. 3. Methods – the people,
processes and technologies that will be affected by data governance strategies. 4. Data
management structures and technologies – the underlying concepts and technologies that can
help establish and enforce data governance at the application or data level. I think in terms of
decision-making power; a good leader needs to make the call by using the big data information
and decision analysis models to integrate the revenue quantification and qualitative indicator
systems.
Hi,
I think in my opinions, the core values and the ideas are the most important organization
culture. First of all, Core values are the fundamental beliefs of a person or organization. There
are some examples about core values for a company: A commitment to sustainability and to
acting in an environmentally friendly way. Companies like Patagonia and Ben & Jerry’s have
environmental sustainability as a core value. 1. A commitment to innovation and excellence.
Apple Computer is perhaps best known for having a commitment to innovation as a core value.
This is embodied by their “Think Different” motto. 2. A commitment to doing good for the
whole. Google, for example, believes in making a great search engine and building a great
company without being evil. It means core value means the value of the organization. For the
ideas, I think ideas are important because I believed a good idea is just like a second life for an
enterprise. If we have good ideas, we could solve the difficult problems or even continue to
create some new things for ourselves. Therefore I think it is important to protect the ideas in
the company.
Email Scenario
In the Netflix Prize and recommendation problem, there is a need for accuracy by
reducing errors. Thus, there are two main objectives of this project. The first one is to educate the
employees about the causes of missing data in the system which reduce accuracy and the second
one is to find the solutions for the missing data (Amatriain & Basilico, 2012). These are
fundamental objectives due to several reasons. First, as employees, people get involved in
several actions which may lead to the loss of data in the process. Loss of data leads to system
errors which lead to poor performance or sometimes failure of the systems. Some of the causes
include programming errors, loss of data during the transfer process, failure of the user to fill in
some required fields, or even ignorance by the users due to personal beliefs about performance.
In this context, an organization is likely to run into significant losses. Can you imagine if the
company lost the details of all the clients due to programming error? It might have to spend lots
of resources to recover from the loss. Thus, under this goal, the data science team will know how
their actions and knowledge about data-driven decisions affect the welfare of the organization.
In the second goal, strategy formulation is an important thing to learn. People need the
data science team needs to know the best practices to keep the data free from errors. This
objective is derived from the first one. Having known the cause, why not formulate a strategy?
Knowing that a problem exists and dealing with it are two different things. Thus, this makes this
objective vital to this project.
There are several questions which the data science team should be able to respond to in
order to make sound recommendations in this project. These questions include:
1. From the previous errors, which kind of incidences in the organization led to their
existence?
2. Are there any identified ways to improve the efficiency of the project? If present, which
ones are they and how can they be of help?
3. Which technologies are at our exposure to help mitigate the risks we encounter on the
way?
References
Amatriain. X., & Basilico. J. (2012, April 06). Netflix Recommendations: Beyond the 5 stars
(Part 1). Retrieved from https://medium.com/netflix-techblog/netflix-recommendationsbeyond-the-5-stars-part-1-55838468f429
Amatriain. X., & Basilico. J. (2012, April 06). Netflix Recommendations: Beyond the 5 stars
(Part 2). Retrieved from https://medium.com/netflix-techblog/netflix-recommendationsbeyond-the-5-stars-part-2-d9b96aa399f5

Purchase answer to see full
attachment

error: Content is protected !!