Study with the several resources on Docsity
Earn points by helping other students or get them with a premium plan
Prepare for your exams
Study with the several resources on Docsity
Earn points to download
Earn points by helping other students or get them with a premium plan
1641 : Business Intelligence - ASM1 - PASS
Typology: Assignments
1 / 31
This page cannot be seen from the preview
Don't miss anything!
Qualification BTEC Level 5 HND Diploma in Computing Unit number and title Unit 14: Business Intelligence Submission date 07/03/2022 Date Received 1st submission Re-submission Date 14/03/2023 Date Received 2nd submission Student Name Dao Truong Vi - Group leader Bui Minh Dung Nguyen Minh Duc Nguyen Gia Huy Student ID
Class GCS0905C Assessor name Ton Nguyen Trong Hien Student declaration I certify that the assignment submission is entirely my own work and I fully understand the consequences of plagiarism. I understand that making a false declaration is a form of malpractice. Student’s signature Grading grid P1 P2 M1 M2 D1 D
Assessment Brief Student Name/ID Number Dao Truong Vi GCS210514 - GL Bui Minh Dung GCS Nguyen Minh Duc GCS Nguyen Gia Huy GCS Unit Number and Title 14: Business Intelligence Academic Year 2023- Unit Tutor Ton Nguyen Trong Hien Assignment Number & Title Assignment 1: Discover business process and BI technologies Issue Date Submission Date 07/03/ IV Name & Date Submission Format The submission is in the form of a Microsoft® PowerPoint® style presentation to be presented to your colleagues. The presentation can include links to performance data with additional speaker notes and a bibliography using the Harvard referencing system. The presentation slides for the findings should be submitted with speaker notes as one copy. You are required to make effective use of headings, bullet points and subsections, as appropriate. Your research should be referenced using the Harvard referencing system. The recommended word limit is 500 words, including speaker notes, although you will not be penalized for exceeding the total word limit.
Unit Learning Outcomes LO1 Discuss business processes and the mechanisms used to support business decision-making. LO2 Compare the tools and technologies associated with business intelligence functionality Assignment Brief Your company is currently working in [Assumed Domain] for 2 years. For a new, young company, the competition in the market is very high. Therefore, the Board of Directors has decided to apply Business Intelligence to improve the company business process by making better decisions. The Board of Directors assigns a small group including you in the Research & Development Department to study business intelligence to apply for the company in the coming years. You need to research business processes and decision support processes in the company and identify the types of data (unstructured, semi-structured or structured) generated by these processes with examples. You also need to research about current software used in the business process or decision support process and evaluate these usages (benefits and drawbacks). Next you need to understand the types of support for decision-making at different levels (operational, tactical and strategic) within the company and study which business intelligence features can help on that type of support. Study the information systems or technologies (of BI) can be used in this case, compare and contrast them to conclude which should be used. Your group needs to present the research results to the board in a presentation of 30 minutes.
Task 1 (P1, M1)
1. Dataset and business processes chosen: The company we have chosen to research about is Ford; Ford is an American automotive company which specializes in designing, manufacturing, marketing, and servicing of vehicles (e.g., cars, trucks, sport vehicles, and electrical vehicles). Ford has many core and supporting business processes: ● Core business processes are those that create products and earn Ford its revenue: ○ Car designing. ○ Car manufacturing. ○ Car selling. ○ Financing/lease contracts to car dealerships. ● Supporting business processes are activities and functions that assist Ford in achieving its core business processes: ○ Accounting. ○ Sales. ○ Customer relation management. ○ Marketing. ○ Human resource. The two datasets our group has chosen discuss the processes of car selling and customer relation management. Main business process: one of Ford's main business processes is car selling, which generates the largest portion of its income through the sale of automobiles, which the following dataset describes. ● This data set is taken from Kaggle, scrapped from 100000 used car listings: https://www.kaggle.com/datasets/adityadesai13/used-car-dataset-ford-and-mercedes?resou rce=download&select=ford.csv
● This dataset is taken from Kaggle, containing consumer's thoughts and the star rating of car manufacturer/model/type ● The dataset has a total of 26760 entries and 7 columns: id, review date, author name, vehicle title, review title, review content, and rating. The second dataset contains both ordinal (i.e., star rating) and nominal data; they are unstructured data generated from the car selling process. ● This dataset is most suitable for those in the tactical level to understand customer relations and how to improve their business processes and products. By analyzing this data, Ford can make informed decisions about how to improve its customer service, marketing, and sales efforts, ultimately leading to increased customer loyalty and satisfaction
2. Data types generated from business processes: The car selling and customer relation processes generated the bellow data type:
● Structured data: this is data that is highly organized and can be easily stored, searched, and analyzed in RDBMS. Examples of structured data generated by the car selling process include: ○ Sales data, such as sales figures, number of cars sold, and revenue generated from cars/services sold.. ○ Customer data, including customer information and purchase history ○ Inventory data such as which types/makes of vehicle has been the most popular. ● Semi-structured data: this is data that has some organization, but is not as easily searchable and analyzed as structured data; they might need some adjustments in order to be used in RDBMS. Examples of semi-structured data generated by the car selling/customer relation process include: ○ Data from social media sites like customer reviews and feedbacks. ○ Web analytics data such as website traffic. ○ Service history data like maintenance. ● Unstructured data: This is data that has no organization or structure and is difficult to search or analyze; massive amounts of effort would be needed to be able to use inside RDBMS. Examples of unstructured data generated by the car selling/customer relation process include: ○ Call recordings from dealerships/call centers, including customer service calls and sales calls. ○ Text-based data, including emails and online chat transcripts from customers. ○ Image and video data, including photos and videos of vehicles, customer testimonials, and promotional materials.
3. Diagrams: 3.1. Activity diagrams:
○ Ford mostly sells their cars through dealerships, instead of directly through customers. However, this is soon to change; if Ford were to sell to their customers directly, this would be how it goes. ○ First, they would receive their customers and show them around the dealerships. Then the salesman would ask the customers for any model that they have in mind and show them the vehicles with such models. ○ When the customer is presented with this option, they can either choose to buy a used or new car; used cars will cost less than new ones depending on their characteristics like mileage. The customer will also have the option to test drive their vehicle before finalizing their purchase. ○ Once the customer has chosen a car, the salesman would get the quote for the vehicle. The customers will also have the option to add on extra services to the car. For example, insurance in case of accidents, or financing if they want to pay over a long period of time. ○ If extra services were added, a new quote would be created and added up in the invoice delivered to the customer. The car selling processes generated 3.2. DFD: Figure 2: DFD for car selling
○ In the serving customer stage, the customers will present the model they want over to the salesman. The salesman will take this request and check the availability of the model in the inventory. The inventory will give the information relating to the model (e.g., where it is in the dealership, status of model) to the salesman, which he will then present to the customers. ○ When the customers have chosen the model, depending on if they want extra services, the car model information will be passed onto the service repository. This repository will present all services available for that car model. ○ Once that is done, we can move on to the invoice stage. The dealership will save the customer’s information in the customer's detail repository for future occasions. The sales information (e.g., car model, salesman ID) will be logged in the sales repository; this repository will update the inventory regarding the car that was just sold. 3.3. CFD: Figure 3: CFD for selling cars ● First, the customer asks the salesman for a specific car model they are interested in. The salesman will then present the car model the customer is interested in. ● The customer will accept the model, then the salesman will ask them if they want to add extra services to their car. The customer can choose whether they want to add extra services or not.
○ Cons: While it is easy to set up NoSQL databases, it is very hard to operate the data on it to make something useful therefore requiring experts to operate it (e.g., data engineers, data scientists). ● Data warehouse: a data warehouse is a centralized data repository, mostly used for analysis and decision making. Data warehouses are designed to support complex reporting and analysis, and they often include data from a wide range of sources. ○ Pros: data warehouses can handle large volumes of data and can be optimized for fast queries and reporting. Not only that, it can help to ensure data quality and consistency. It provides a centralized database where data scientists can create reports and predictions ○ Cons: data warehouses are complex to set up and operate. They need experts who can set them up and operate them. ● Cloud storage: refers to data storage based in a cloud-based environment, where data can be accessed over the Internet anywhere, anytime. They offer a wide range of services from simple storage to advanced analytics. ○ Pros: highly scalable and flexible on-demand storage, making it easy to add data and increase data storage capacity. It is also highly accessible, as data can be accessed from anywhere with an internet connection ○ Cons: data is stored off-premise and is subject to potential security breaches. Additionally, cloud storage may have limitations in terms of performance and data access speeds, depending on the business bandwidths. ● Distributed storage: a type of storage system that stores data across multiple servers or nodes in a network. These nodes work together to provide a single collective storage pool that appears as a one storage device to the end-users ○ Pros: distributed storage systems can provide high performance for both read and write operations because the data are separated through multiple nodes. They are also a highly scalable solution.
○ Cons: distributed storage systems are more complex than traditional storage technology because they require coordination between multiple nodes; they also create more points of failures. Data analytic tools: ● Tableau: tableau is a data visualization and business intelligence, created for businesses to create interactive dashboards, graphs, and reports. It has a wide range of features that allows real-time data analysis and processing. ○ Pros: ■ Required little knowledge to use and has good UI and UX designs. ■ Allows users to turn raw data into diagrams, graphs, and dashboards. ■ Can work with a variety of file types. ■ Has real-time data processing and analysis. ○ Cons: ■ Rather expensive for large scale enterprises. ■ Might take a long time to execute depending on dataset sizes and complexity. ■ Need advanced skills to apply complex techniques. ● Excel: excel is a spreadsheet program that organizes information into rows and columns, allowing users to organize and analyze data. It offers a wide range of statistical functions and analysis tools, with a user-friendly interface ○ Pros: ■ Cheap and available for most users and workstations. ■ Has a variety of tools and functions for data analysis. ■ Has a friendly user interface. ■ A lot of existing and free knowledge of excel exist online ○ Cons: ■ Large datasets can cause performance issues. ■ Data visualization is rather lacking compared to other tools. ■ Does not support a variety of file type, requiring manual inputs and formatting.
sensitive to outliers and errors in data, requiring data filtering before it can be applied. ● Cluster analysis: a method commonly used to identify patterns and relationships in data by grouping objects or data points into clusters based on their similarities or differences. ○ Pros: help identify groups or segments of data that share common characteristics, thereby exposing the hidden patterns. It can also be used for data reduction and visualization. ○ Cons: sensitive to outliers, errors in data, and the way the data was clustered ● Sentiment analysis: a method used to identify and extract subjective information from textual data, such as opinions, attitudes, and emotions; a tool commonly used in analyzing customer’s feedbacks. ○ Pros: provide valuable insights into customer opinions and attitudes, which can be used for brand monitoring, reputation management, and how to improve business processes. ○ Cons: challenging to accurately identify the sentiment of the texts, as language can be ambiguous and may be influenced by factors such as sarcasm or irony. ● Data mining: a process of discovering patterns and relationships in large datasets using statistical and machine learning techniques. ○ Pros: help identify hidden patterns and relationships in large datasets, and can be used for predictive modeling and forecasting. ○ Cons: requires a large amount of data, if not the data may be wrong because of small sample sizes. It can also be affected by biases in the data. From the above analysis in combination with the dataset, I recommend Ford use the following tools to support their business processes: ● Storage technology: it is recommended for someone at the size of Ford to use a combination of cloud storage for their day-to-day operation. ○ Cloud storage is highly scalable, which means it can handle large volumes of data without any hassle. For a company the size of Ford and the amount of data they generate on a daily basis, high scalability is much needed. ○ Cloud storage provides a platform for teams to collaborate on data, making it easier to share information and work together on complex BI projects.
○ Some cloud services also provide analytic technology, for example Google Cloud Platform offers services such as BigQuery for data warehousing, Dataflow for big data processing, and Looker for business intelligence. ● Data analytic tools: I recommend using a combination of Tableau and Excel as data analytics tools ○ Tableau is a data visualization and exploration tool that can help Ford gain insights from its data. With Tableau, Ford can create interactive dashboards and visualizations to analyze trends and patterns in their data. Tableau also allows for quick exploration of data, enabling users to find specific information quickly. Tableau would be used by those making tactical and strategic decisions. ○ Excel is a widely used tool for data analysis and manipulation. It's familiar to most users, and its ease of use makes it a popular tool for every day analysis and reports; it can be used for everyday operations like generating reports. Excel would mostly be used for those making operational decisions. ● Data analysis technique: I recommend using sentiment analysis and machine learning ○ Sentiment analysis can be used to gain insights into how customers feel about their products and services. This can help Ford to understand their customers better and tailor their marketing and customer service strategies according to such needs. ○ Machine learning can be used to build predictive models based on past data, enabling Ford to forecast trends and anticipate demand, thereby optimizing their operations. For example, we can use machine learning to predict which models will be most popular in the coming season, helping Ford to allocate resources more efficiently toward marketing or sales. Task 2 (P2, M2, D1, D2)
1. Decision making process: 1.1. Overview: The decision-making process is a step-by-step process allowing professionals to solve problems by weighing evidence, examining alternatives, and choosing a path from there. This defined process also provides an opportunity, at the end, to review whether the decision was the right one. There are 3 levels of decision making in a company. They are:
