Business Analytics Quiz with Answers PDF

> It is the interpretation of historical data to identify trends and patterns. It also uses data to understand the past and the present. Answer: DESCRIPTIVE ANALYTICS > It is the process of uncovering patterns and other valuable information from large data sets. Answer: DATA MINING > [TR...

> It is the interpretation of historical data to identify trends and patterns. It also uses data to understand the past and the present. Answer: DESCRIPTIVE ANALYTICS > It is the process of uncovering patterns and other valuable information from large data sets. Answer: DATA MINING > [TRUE/FALSE] Analytics is solely focused on using data to make better business decisions. Answer: FALSE > Business Analytics refers to the statistical methods and computing technologies for ______, ______, and ______ data to uncover patterns, relationships, and insights that enable better business decision-making. Answer: PROCESSING, MINING AND VISUALIZING > An external data source which provides valuable insights into consumer behavior and preferences, allowing companies to tailor their marketing strategies? Answer: SOCIAL MEDIA DATA > Given the scenario of ‘A retail company wants to analyze its sales data’, what type of analytics best describes “Scrutinizing factors such as pricing changes, marketing campaigns or economic conditions to deduce sales dip”? Answer: DIAGNOSTIC ANALYTICS > List 2 social media metrics that measures audience engagement. Answer: LIKES, SHARES, COMMENTS, CLICK-THROUGH RATES > [TAMA/MALI] The analytics lifecycle includes data preparation and management to analysis and reporting. Answer: MALI > A branch of Artificial Intelligence (AI) and computer science that focuses on the using data and algorithms to enable AI to imitate the way that humans learn, gradually improving its accuracy. Answer: MACHINE LEARNING > These are the columns that describes the data stored in a database file. Answer: FIELDS > [ACRONYM] CRUD Answer: CREATE. READ. UPDATE. DELETE > [RIGHT/WRONG] Databases are always the primary data source for business analytics. Answer: WRONG > Which is a centralized repository specifically designed for storing, managing, and analyzing large volumes of data for business intelligence purposes? Answer: DATABASE > [TYPE OF DATA] Product Name || Purchase Date || Purchase Quantity || Sales Amount || Customer Satisfaction Rating Answer: NOMINAL/CATEGORICAL || INTERVAL || RATIO || RATIO || ORDINAL > In number of sales or customers, continuous or discrete is used to measure data in positive integers? Answer: DISCRETE > With the solution from the previous example, where does the numerical values come from? Sales = 500 – 0.05(price) + 30(coupons) + 0.08(advertising) + 0.25(price)(advertising) Answer: MULTIPLE LINEAR REGRESSION ANALYSIS > With the solution from the previous example: what do you call the numerical values? Answer: COEFFICIENT > [TRUE/FALSE] Data modelling serves as a tool that can help organizations forecast the potential possibilities brought by particular actions. Answer: TRUE > The formula S=aebect, where S is sales, t is time, a, b, and c are constants, e is base of _________. Answer: NATURAL LOGARITHM > A visual representation which help stakeholders understand complex decision-making scenarios by breaking down the problem into its constituent parts and illustrating the relationships between different factors. Answer: DECISION MODEL > It clarifies how different factors influence the final outcome. Answer: RULES > [TAMA/MALI] The decision node in a decision tree represents a single business rule. Answer: MALI > They’re the representation of the information available when making a choice. Answer: CONDITION / INPUT > In the problem-solving process using analytics, which stage involves the exploration and discovery of meaningful patterns within the data? Answer: ANALYZING THE PROBLEM > Launching a new product can either be successful or failure. If the product fails, _______ or _______ are the possible next steps for the company according to the diagram. Answer: RE-MARKET OR DISCONTINUE > [RIGHT/WRONG] Data modeling is the process of visually mapping out how decisions are made within an organization. Answer: WRONG > In the formula: S = aebect, what is the numerical value of e? Answer: 2.71828 > [YES/NO] Decision tree provides a simplified representation of the decision-making process and may not capture all possible outcomes or actions. Answer: YES > A decision tree is used to prevent decisions and their potential consequences in _________. Answer: BRANCHING STRUCTURE > A decision model is used to prevent decisions and their potential consequences in branching structures. Answer: DECSION TREE > It is a visual representation of a process which show how data and knowledge are merged together to make a particular business decision. Answer: DECISION MODEL > [TAMA/MALI] Tree leaf node in a decision tree represents a single business rule. Answer: TAMA > From the steps in problem solving with analytics, what step sets the stage for a systematic investigation? Answer: STRUCTURING THE PROBLEM > In this step the translation of analytical findings into actionable insights happen. Answer: INTERPRETING THE RESULT AND MAKING DECISIONS > The factors that impact the decision-making is called _________. Answer: CONDITION / INPUT > [TRUE/FALSE] A decision model using business analytics enables a business to make data- driven decisions by predicting sales outcomes. Answer: TRUE > It exists when there is something between the present and the expected. Answer: PROBLEM > The formula S=aebect, S is sales, e is base of natural logarithm, t is time and a, b, and c are _________. Answer: CONSTRAINTS > These serve as visual aids, helping all involved stakeholders, including analysts and key decision-makers, to comprehend all the important factors, business rules, and considerations that impact choices within an organization. Answer: DECISION MODEL > What is the model used to get the Sales from the previous example? Sales = 500 – 0.05(price) + 30(coupons) + 0.08(advertising) + 0.25(price)(advertising) Sales = (500 - 0.05 × $6.99) + (30 × 0) + (0.08 × 0) + (0.25 × 6.99 × 0) Sales = 500 units Answer: LINEAR REGRESSION MODEL BUSINESS ANALYTICS METHODOLOGIES is then used for strategic decision- » Descriptive: uses data to understand making to improve business outcomes past and present; describes the data » Data Mining/Knowledge Discovery in it contains Data (KDD): the process of -The interpretation of historical uncovering patterns and other data to identify trends and patterns valuable information from large data -An example would be a pie chart that sets. A significant component of big breaks down the demographics of a data analytics company’s customers. » Data Warehousing: EDW (Enterprise » Diagnostic: helps pinpoint the root Data Warehouse) - system that cause of an event; provides crucial aggregates data from different information about why a trend sources, including apps, IoT occurred devices, social media and -The interpretation of historical spreadsheets into a single, central, data to determine why something has consistent data store to support happened data analysis, data mining, AI and -For example, manufacturers can analyze a machine learning (ML). A data failed component on an assembly line and warehouse system enables an determine the reason behind its failure. organization to run powerful » Predictive: mines existing data, analytics on large amounts of data identifies patterns and helps (petabytes and petabytes) in ways companies predict what might happen that a standard database cannot. in the future based on that data; » Data Visualization: representation analyzes past performance of data by using graphics such as -The use of statistics to forecast charts, plots, infographics and even future outcomes animations. It can also help with -For example, an organization could make idea generation, idea illustration predictions about the change in coat or visual discovery. sales if the upcoming winter season is » Forecasting: tool takes historical projected to have warmer temperatures. data and current market conditions » Prescriptive: help organizations and then makes predictions as to how make decisions about the future much revenue an organization can based on existing information and expect to bring in over the next few resources by reviewing their months or years existing data to make a guess about Forecasts - adjusted as new information what will happen next; uses becomes available optimization techniques » Machine Learning Algorithms: a set -The application of testing and of rules or processes used by an AI other techniques to determine which system to conduct tasks, most often outcome will yield the best result to discover new data insights and in a given scenario patterns, or to predict output -For example, marketing and sales values from a given set of input organizations can analyze the lead variables. It enables machine success rates of recent content to learning to learn, delivering the determine what types of content they power to analyze data, identify should prioritize in the future. trends and predict issues before -Descriptive analytics describes what has they occur happened over a given period. Diagnostic ML is a branch of AI and computer science analytics focuses more on why something that focuses on the using data and happened. Predictive analytics moves to algorithms to enable AI to imitate the what is likely going to happen in the way that humans learn, gradually near term. Finally, prescriptive improving its accuracy. analytics suggests a course of action. » Reporting: Business analytics runs on the fuel of data to help BUSINESS ANALYTICS TOOLS & TECHNIQUES organizations make informed » Data Management: the practice of decisions. Enterprise- ingesting, processing, securing and grade reporting software can extract storing an organization’s data. It information from various  applications used by an enterprise, Market basket analysis: Understanding analyze the data and generate product relationships and recommending reports complementary items. » Statistical Analysis: enables an Customer churn prediction: Predicting organization to extract actionable which customers are likely to leave. insights from its data. Advanced Targeted marketing: Creating statistical analysis procedures help personalized campaigns based on ensure high accuracy and quality customer preferences. decision-making. The analytics Healthcare lifecycle includes data preparation Disease prediction: Identifying risk and management to analysis and factors and predicting disease reporting outbreaks. » Text Analysis: Identifies textual Personalized medicine: Tailoring patterns and trends within treatments based on individual patient unstructured data by using machine data. learning, statistics and Healthcare fraud detection: Detecting linguistics. By transforming the anomalies in medical claims. data into a more structured format Finance through text mining and text Fraud detection: Identifying analysis, more quantitative insights fraudulent transactions and can be found. activities. ------- Risk assessment: Evaluating financial DATA FOR BUSINESS ANALYTICS risks and making informed decisions. » Metrics: These are quantifiable Customer churn prediction: Predicting values used to track and assess performance. They provide a standard customer attrition in banking and for measuring progress towards a insurance. E-commerce specific goal. » Measures: These are specific data Product recommendation: Suggesting points or values that contribute to products based on customer purchase a metric. They are the raw data used history. to calculate metrics. Customer segmentation: Identifying For example, "customer satisfaction" is a high-value customers and tailoring metric, while "average customer marketing efforts. satisfaction score" is a measure. Inventory management: Optimizing stock » Discrete metrics are those that can levels based on demand patterns. be counted in whole numbers. They Government represent distinct and separate Public safety: Predicting crime values. countable, whole numbers hotspots and optimizing resource Ex. Number of customers, number of allocation. products sold, number of customer Fraud detection: Identifying complaints, number of website visits fraudulent activities in government » Continuous metrics are those that programs. can take on any value within a Policy analysis: Evaluating the specific range. They are measured impact of government policies on rather than counted. measurable, can various. have decimal points Science & Research Ex. Revenue, profit margin, time spent on Scientific discovery: Uncovering new website, average order value patterns and insights in scientific ------ data. SCOPE OF DATA MINING Drug discovery: Identifying potential Business & Marketing drug candidates and understanding Customer segmentation: Identifying their interactions. distinct groups of customers based on Climate modeling: Analyzing climate shared characteristics. data to predict future trends. DATA MINING TASKS analyzed together to extract meaningful Anomaly detection: identify data points insights. that is significantly different from DATA MINING ARCHITECTURE normal patterns; e.g. detecting 1. Data Collection: Data is gathered from fraudulent credit card transactions various sources and stored in the Algorithm: Statistical methods (e.g., Z- database or data warehouse. score, Mahalanobis distance), One-Class 2. Data Mining: The data mining engine SVM, Isolation Forest processes the data to discover Association rule learning: discover patterns. interesting relationship between 3. Pattern Evaluation: The discovered variables in a dataset; e.g. finding patterns are analyzed and evaluated products that are frequently purchased for their significance. together 4. Knowledge Extraction: Valuable Algorithm: Apriori, FP-growth, GSP insights and knowledge are extracted Clustering: group similar data points from the patterns and stored in the together; e.g. segmenting customers knowledge base. into distinct groups based on 5. User Interface: The user interface preference or behaviors provides tools for visualizing and Algorithm: K-means, Hierarchical interpreting the results. Clustering, DBSCAN, Gaussian Mixture KDD ARCHITECTURE Models Some people treat data mining same as Classification: predict categorical Knowledge discovery while some people labels for data points; e.g. predicting view data mining essential step in whether a customer will stop using a process of knowledge discovery. Here is product based on demographics and the list of steps involved in knowledge purchase history discovery process: Algorithm: Decision trees, Naive Bayes, Data Cleaning - In this step the noise Support Vector Machines (SVMs), Neural and inconsistent data is removed. Networks, Random Forest Data Integration - In this step multiple Regression: predict numerical values data sources are combined. based on input variables; e.g. Data Selection - In this step relevant to predicting house prices based on the analysis task are retrieved from the features like sqm, bedrooms, location database. Algorithm: Linear Regression, Logistic Data Transformation - In this step data Regression, Decision Trees, Random are transformed or consolidated into Forest, Support Vector Regression forms appropriate for mining by performing summary or aggregation Summarization: summarize large datasets operations. into more concise form; e.g. generating Data Mining - In this step intelligent summary of a customer’s purchase methods are applied in order to extract history data patterns. Algorithm: Text summarization techniques Pattern Evaluation - In this step, data (e.g., extractive summarization, patterns are evaluated. abstractive summarization), numerical Knowledge Presentation - In this step, data summarization (e.g., mean, median, knowledge is represented. mode, standard deviation) ----- DATA POINTS: individual piece of data BIG DATA ANALYTICS that represents specific observation or Big data analytics describes the process measurement; ex. weather reading, of uncovering trends, patterns, and customer transaction, traffic data, etc. correlations in large amounts of raw data DATASET: collection of related data to help make data-informed decisions. It points; ex. daily weather record for a is the use of advanced analytic region, customer transactions from a techniques against very large, diverse local business, traffic data collected data sets that include structured, semi- from various intersections structured and unstructured data, from *Data points are the building blocks of a different sources, and in different sizes dataset. Dataset is composed of multiple from terabytes to zettabytes. data points that are organized and  Hadoop is an open-source framework that efficiently stores and processes big datasets on clusters of commodity hardware. This framework is free and can handle large amounts of structured and unstructured data, making it a valuable mainstay for any big data operation. NoSQL databases are non-relational data management systems that do not require a fixed scheme, making them a great option for big, raw, unstructured data. NoSQL stands for “not only SQL,” and these databases can handle a variety of data models. MapReduce is an essential component to the Hadoop framework serving two functions. The first is mapping, which filters data to various nodes within the cluster. The second is reducing, which organizes and reduces the results from each node to answer a query. YARN stands for “Yet Another Resource Negotiator.” It is another component of second-generation Hadoop. The cluster management technology helps with job scheduling and resource management in the cluster. Spark is an open-source cluster computing framework that uses implicit data parallelism and fault tolerance to provide an interface for programming entire clusters. Spark can handle both batch and stream processing for fast computation. Tableau is an end-to-end data analytics platform that allows you to prep, analyze, collaborate, and share your big data insights. Tableau excels in self-service visual analysis, allowing people to ask new questions of governed big data and easily share those insights across the organization.