MBA(A) 115 Data Preparation and Exploration Notes cover all 4 units of this GGSIPU MBA (Analytics) Semester 1 core paper in a 54-page book: 25 worked R code examples, 19 figures, 24 solved short answers and 28 long-answer practice questions, mapped to the Scheme and Syllabus 2022-24 onwards.
Written by Prateek Talwar, Founder, Unnati Educations · Reviewed by Ritik Rawat, B.Tech, Senior Full Stack Developer · Checked against GGSIPU MBA (Analytics) Scheme and Syllabus 2022-24 onwards (syllMBAAnalytics180225.pdf) · Updated 14 October 2026 · Editorial policy
Scheme: MBA (Analytics) Scheme and Syllabus 2022-24 onwards | Applies to: batches under the 2022-24 onwards scheme (Semesters 1-2 approved by the Academic Council on 22.03.2023) | Verified against: syllMBAAnalytics180225.pdf, ipu.ac.in
MBA(A) 115 Data Preparation and Exploration at a glance: GGSIPU MBA (Analytics) Sem 1 credits, units and exam pattern
Every row comes from the official PDF; where it is silent, the row says so.
| Code and title | MBA(A) 115 Data Preparation and Exploration |
|---|---|
| Course and semester | MBA (Analytics), First Semester |
| Category and credits | Core · L 2, no T/P · 2 credits (28 unit hours) |
| Marks | Internal 25 (Class Test-I 15 + presentation, viva or GD 10). End-term marks and total not printed in the official PDF. |
| Applies to | Scheme and Syllabus 2022-24 onwards (Semesters 1-2 approved on 22.03.2023) |
| End-term pattern | Paper-setter instructions not printed in the official PDF |
| Paired lab | MBA(A) 155 Lab · Skill Enhancement · P 2 · 1 credit |
| Official syllabus | MBA (Analytics) Scheme and Syllabus 2022-24 onwards (PDF) |
The scheme follows GGSIPU Ordinance 11 for end-term minimums and re-appear rules.
MBA(A) 115 is one of 11 papers in the GGSIPU MBA (Analytics) Semester 1 papers, worth 25 credits together.
MBA(A) 115 Data Preparation and Exploration Notes unit-wise: 25 R code examples and 24 solved short answers across 4 units
These Data Preparation and Exploration notes in English follow the four official units, print every R program with its output and use Indian data such as RBI and CMIE.
Notes for other papers of this course: GGSIPU MBA (Analytics) notes.
MBA(A) 115 Unit 1: Data Preparation
Pages 5 to 18, 8 sections. Open versus paid data sources, the DIKW pyramid, levels of measurement, enterprise and consumer data, imports with read.csv(), readxl, jsonlite and DBI, metadata, a data dictionary and a CRM-to-billing map. 4 R examples, 6 figures, 1 case study.
| Type | Question it answers | Sales-file example |
|---|---|---|
| Structural | How is it organised? | 6 columns; qty integer, price numeric |
| Administrative | Who owns and may use it? | Sales MIS team; managers only |
| Business | What does each term mean? | Net sales = gross sales − returns − discount |
| Provenance | Where from, and what was done? | POS extract, duplicates removed |
Quick look: four metadata types for a sales file (from page 15)
- Type
- Structural
- Question it answers
- How is it organised?
- Sales-file example
- 6 columns; qty integer, price numeric
- Type
- Administrative
- Question it answers
- Who owns and may use it?
- Sales-file example
- Sales MIS team; managers only
- Type
- Business
- Question it answers
- What does each term mean?
- Sales-file example
- Net sales = gross sales − returns − discount
- Type
- Provenance
- Question it answers
- Where from, and what was done?
- Sales-file example
- POS extract, duplicates removed
MBA(A) 115 Unit 2: Data Pre-processing
Pages 19 to 29, 10 sections. Eleven raw-data anomalies, missing-data types, IQR and z-score outliers, and a de-duplication case (12 lakh members down to 9.1 lakh). Cleaning uses duplicated(), trimws(), gsub() and pmin(). Then transformation, normalisation and feature scaling. 8 R examples, 3 worked illustrations, 3 figures.
| Method | Formula | Scaled values |
|---|---|---|
| Min-max | (x − min) / (max − min) | 0, 0.25, 0.50, 0.75, 1.00 |
| Z-score | (x − mean) / SD | −1.265, −0.632, 0, 0.632, 1.265 |
| Robust | (x − median) / IQR | −1.0, −0.5, 0, 0.5, 1.0 |
| Decimal | x / 102 | 0.20, 0.30, 0.40, 0.50, 0.60 |
Quick look: salaries of Rs. 20-60 thousand, scaled four ways (from page 28)
- Method
- Min-max
- Formula
- (x − min) / (max − min)
- Scaled values
- 0, 0.25, 0.50, 0.75, 1.00
- Method
- Z-score
- Formula
- (x − mean) / SD
- Scaled values
- −1.265, −0.632, 0, 0.632, 1.265
- Method
- Robust
- Formula
- (x − median) / IQR
- Scaled values
- −1.0, −0.5, 0, 0.5, 1.0
- Method
- Decimal
- Formula
- x / 102
- Scaled values
- 0.20, 0.30, 0.40, 0.50, 0.60
MBA(A) 115 Unit 3: Data Exploration
Pages 30 to 41, 11 sections. EDA versus confirmatory analysis, a quick EDA on mtcars, Anscombe's quartet, tool selection by variable type and seven EDA guidelines. PCA on iris keeps 95.8% of variance in two components, LDA classifies 147 of 150 flowers, and NMF finds two shopping baskets. 5 R examples, 4 figures.
| Basis | PCA | LDA | NMF |
|---|---|---|---|
| Learning | Unsupervised | Supervised | Unsupervised |
| Data needed | Any numeric | Numeric + class labels | Non-negative only |
| Objective | Maximum variance | Class separation | Non-negative reconstruction |
| Unique solution | Yes | Yes | No |
Quick look: PCA, LDA and NMF side by side (from page 40)
- Basis
- Learning
- PCA
- Unsupervised
- LDA
- Supervised
- NMF
- Unsupervised
- Basis
- Data needed
- PCA
- Any numeric
- LDA
- Numeric + class labels
- NMF
- Non-negative only
- Basis
- Objective
- PCA
- Maximum variance
- LDA
- Class separation
- NMF
- Non-negative reconstruction
- Basis
- Unique solution
- PCA
- Yes
- LDA
- Yes
- NMF
- No
MBA(A) 115 Unit 4: Data Illustration
Pages 42 to 53, 6 sections. Scatter diagrams with an advertising and sales example (r = 0.9963), other relationship charts, K-means clustering, Type I and II errors, testing steps and four inference examples in R. 8 R examples, 6 figures, 1 case study.
Quick look: testing a "30-minute delivery" claim (from page 51)
d <- c(32, 35, 29, 31, 34, 36, 30, 33, 37, 32)
t.test(d, mu = 30)
# t = 3.5254, df = 9, p-value = 0.00646p = 0.006 < 0.05, so the 30-minute claim is rejected.
Processed and unprocessed data in business analytics: excerpt from page 19 of the MBA(A) 115 notes
Excerpt from page 19
Data pre-processing: an introduction
Data pre-processing is the set of techniques used to turn raw (unprocessed) data into a clean, consistent and analysis-ready (processed) form. It covers finding and fixing errors, handling missing values and outliers, removing duplicates, converting formats, transforming variables and bringing them to a common scale.
Real-world data is dirty. It is incomplete (missing values), noisy (errors and outliers) and inconsistent (different codes and formats). Pre-processing removes these problems so that analytical tools and machine-learning algorithms give reliable results.
The work falls into four major tasks: data cleaning (missing values, noise, outliers, duplicates), data integration (combining data from many sources), data transformation (normalising, scaling, encoding, deriving) and data reduction (fewer rows or columns carrying the same information).
Unprocessed (raw) data
Unprocessed data, also called raw or primary data, is data in the original form in which it was collected, before any checking, cleaning or organisation. Typical examples are a POS export with duplicate bills, a Google Form survey sheet with blank answers and spelling variations, or sensor readings with sudden spikes.
Processed data
Processed data has been cleaned, validated, organised, transformed and documented so that it can be used straight away for analysis, reporting and modelling. An example is a monthly sales table with standard product codes, no duplicates, missing values treated and all amounts in one currency.
| Basis | Unprocessed (raw) data | Processed data |
|---|---|---|
| Form | Original form as collected | Cleaned, organised and transformed |
| Quality | Contains errors, gaps, duplicates, outliers | Accurate, complete and consistent |
| Structure | Often unstructured or messy | Structured tables with defined types |
| Usability | Not directly usable for analysis | Ready for analysis and reporting |
| Volume | Usually larger, with redundant data | Smaller and relevant |
| Meaning | Little meaning without context | Meaningful information with metadata |
| Storage | Data lake or staging area | Data warehouse or analytical database |
| Example | Raw survey sheet with "Dlhi", "delhi" and a blank age | Survey table with city = "Delhi" and age imputed |
Difference between processed and unprocessed data (excerpt, page 19)
- Basis
- Form
- Unprocessed (raw) data
- Original form as collected
- Processed data
- Cleaned, organised and transformed
- Basis
- Quality
- Unprocessed (raw) data
- Contains errors, gaps, duplicates, outliers
- Processed data
- Accurate, complete and consistent
- Basis
- Structure
- Unprocessed (raw) data
- Often unstructured or messy
- Processed data
- Structured tables with defined types
- Basis
- Usability
- Unprocessed (raw) data
- Not directly usable for analysis
- Processed data
- Ready for analysis and reporting
- Basis
- Volume
- Unprocessed (raw) data
- Usually larger, with redundant data
- Processed data
- Smaller and relevant
- Basis
- Meaning
- Unprocessed (raw) data
- Little meaning without context
- Processed data
- Meaningful information with metadata
- Basis
- Storage
- Unprocessed (raw) data
- Data lake or staging area
- Processed data
- Data warehouse or analytical database
- Basis
- Example
- Unprocessed (raw) data
- Raw survey sheet with "Dlhi", "delhi" and a blank age
- Processed data
- Survey table with city = "Delhi" and age imputed
How to write MBA(A) 115 answers: R-backed short answers and ten-to-fifteen-mark answers built on comparison tables
MBA(A) 115 mixes management theory with R, so a strong answer has three layers: a one-line definition, a table or step flow, and one R function or small numerical that proves the point. The notes' exam tips follow this shape.
Comparison questions. For open versus paid sources, write meaning, four examples, five characteristics and three uses for each side, then close with the comparison table from page 8. The same build works for PCA versus LDA.
Data cleaning questions. Take missing values, duplicates, outliers, inconsistent text, wrong data types and invalid values in turn: one line of meaning, one technique and one R function each, such as na.omit(), duplicated(), trimws() or as.numeric(). Put it in a table.
Hypothesis testing questions. State the decision rule in words ("Since p-value (0.006) < α (0.05), we reject H0"), then say what it means for the business. The notes stress that interpretation earns marks of its own.
Worked example (page 21): the IQR rule for outliers. Incomes (Rs. thousand) of 11 customers: 28, 32, 35, 30, 31, 29, 34, 33, 36, 30, 250. Q1 = 30 and Q3 = 34.5, so IQR = 4.5. Lower fence = 30 − 1.5 × 4.5 = 23.25; upper fence = 34.5 + 1.5 × 4.5 = 41.25. As 250 is above 41.25, it is an outlier. End with the business point: the mean (568 ÷ 11 = 51.6) is distorted while the median (32) is not.
Two habits from the notes help in any unit: check every import with head(), str(), dim() and sum(is.na()), and compute scaling parameters on training data only, to avoid data leakage. Practise this format on GGSIPU MBA (Analytics) important questions.
MBA(A) 115 exam corner: 24 solved short answers and 28 ten-to-fifteen-mark practice questions by unit
Each unit ends with six solved short answers and seven long "Practice Questions (10–15 Marks)". These are exam-style questions; the book has no year tags.
| Unit | Short answers (solved) | Long answers (10–15 Marks, practice) | R code examples |
|---|---|---|---|
| 1 Data Preparation | 6 | 7 | 4 |
| 2 Data Pre-processing | 6 | 7 | 8 |
| 3 Data Exploration | 6 | 7 | 5 |
| 4 Data Illustration | 6 | 7 | 8 |
MBA(A) 115 exam questions and R code examples by unit
- Unit
- 1 Data Preparation
- Short answers (solved)
- 6
- Long answers (10–15 Marks, practice)
- 7
- R code examples
- 4
- Unit
- 2 Data Pre-processing
- Short answers (solved)
- 6
- Long answers (10–15 Marks, practice)
- 7
- R code examples
- 8
- Unit
- 3 Data Exploration
- Short answers (solved)
- 6
- Long answers (10–15 Marks, practice)
- 7
- R code examples
- 5
- Unit
- 4 Data Illustration
- Short answers (solved)
- 6
- Long answers (10–15 Marks, practice)
- 7
- R code examples
- 8
- Unit 1: What is first-party and third-party consumer data? Own customers (website, app, loyalty card) versus data bought from brokers.
- Unit 2: What are MCAR, MAR and MNAR? Three missing-data types, driven by chance, other observed variables, or the missing value itself.
- Unit 3: Why is LDA called supervised? It uses known class labels to separate classes; PCA ignores labels.
- Unit 4: Distinguish between Type I and Type II errors. Type I rejects a true H0 (α); Type II fails to reject a false H0 (β).
The MBA(A) 115 notes solve 24 short-answer questions and list 28 long-answer practice questions (10–15 Marks) across 4 units, plus 25 R code examples.
More practice sits in the MBA(A) 115 important questions.
MBA(A) 115 and the MBA(A) 155 data preparation lab, plus other GGSIPU MBA (Analytics) Sem 1 papers
Paired lab: MBA(A) 155 Data Preparation and Exploration lab notes · Skill Enhancement · P 2 · 1 credit. The official PDF says this lab is based on MBA(A) 115.
The official MBA(A) 155 outline names four areas, each taught here:
- Normalisation tools → Unit 2, pages 26 to 29
- Principal Component Analysis → Unit 3, pages 36 to 38 (
prcomp()) - Linear Discriminant Analysis → Unit 3, pages 38 to 39 (
lda()) - Data illustration and other techniques → Unit 4, plus Unit 2 cleaning (pages 23 to 25)
Other Semester 1 papers are MBA(A) 101 Management Process and Organisational Behaviour, MBA(A) 103 Accounting for Management, MBA(A) 105 Economics and Quantitative Analysis, MBA(A) 107 Information Technology for Management, MBA(A) 109 Communication in Organizations, MBA(A) 111 Marketing Management, MBA(A) 113 Introduction to Analytics and R, and the labs MBA(A) 151 and MBA(A) 153; MBA(A) 113 and its R lab sit closest to this paper.
Who writes and checks the MBA(A) 115 data preparation notes?
- Prateek Talwar, author · Founder, Unnati Educations · Associate Company Secretary (ACS), ICSI, membership no. 58704, since 15 May 2019 · B.Com, University of Delhi (School of Open Learning), 2012 · Author profile
- Ritik Rawat, subject reviewer for the R code and data sections · Senior Full Stack Developer, Unnati Educations · B.Tech · Reviewer profile
The GGSIPU MBA (Analytics) Sem 1 Data Preparation and Exploration notes are mapped to the 2022-24 onwards scheme. The 2026-27 edition is one 54-page book with 25 R programs, 19 figures and 3 case studies. Last updated 14 October 2026; corrections follow our editorial policy.
The same team prepares GGSIPU important questions for the courses it covers.
Do the MBA(A) 115 notes cover the full GGSIPU syllabus?
Yes. Every official topic in all four units has its own section in the notes; no gaps.
| Official unit | Official topics | Where in the notes | Status |
|---|---|---|---|
| I Data Preparation | Open and paid data sources, uses and characteristics; knowledge development; types of data; enterprise and consumer data; importing data from different formats; metadata meaning and purpose; organizing and mapping metadata | Sections 1-8, p5-17 | Covered |
| II Data Pre-processing | Processed and unprocessed data; anomalies; impact on analytical operations; tools and their properties; cleaning techniques and functions; transforming incorrect data; normalizing datasets; feature scaling | Sections 1-10, p19-29 | Covered |
| III Data Exploration | Meaning, importance, limitations; tools and their properties; selecting tools for different types of data; guidelines; PCA, LDA and Non-negative Matrix Factorization | Sections 1-11, p30-41 | Covered |
| IV Data Illustration | Scatter diagrams and other graphical techniques; clustering to evaluate correlations; principles of hypothesis testing; drawing inferences | Sections 1-6, p42-53 | Covered |
Official MBA(A) 115 syllabus mapped to the notes
- Official unit
- I Data Preparation
- Official topics
- Open and paid data sources, uses and characteristics; knowledge development; types of data; enterprise and consumer data; importing data from different formats; metadata meaning and purpose; organizing and mapping metadata
- Where in the notes
- Sections 1-8, p5-17
- Status
- Covered
- Official unit
- II Data Pre-processing
- Official topics
- Processed and unprocessed data; anomalies; impact on analytical operations; tools and their properties; cleaning techniques and functions; transforming incorrect data; normalizing datasets; feature scaling
- Where in the notes
- Sections 1-10, p19-29
- Status
- Covered
- Official unit
- III Data Exploration
- Official topics
- Meaning, importance, limitations; tools and their properties; selecting tools for different types of data; guidelines; PCA, LDA and Non-negative Matrix Factorization
- Where in the notes
- Sections 1-11, p30-41
- Status
- Covered
- Official unit
- IV Data Illustration
- Official topics
- Scatter diagrams and other graphical techniques; clustering to evaluate correlations; principles of hypothesis testing; drawing inferences
- Where in the notes
- Sections 1-6, p42-53
- Status
- Covered
Official source: MBA (Analytics) Scheme and Syllabus 2022-24 onwards, PDF pages 22 to 23.
Every course in GGSIPU notes is checked against its official PDF the same way.
MBA(A) 115 data preparation notes FAQs
How do I get the full MBA(A) 115 notes?
Tap "Get Full Notes" at the top of this page to message us on WhatsApp at 9899436384. The full MBA(A) 115 notes come only as a 54-page printed book, not as a PDF. Once your order is confirmed, the book is sent to your address, and delivery takes at most 5 to 7 days depending on your location.
Is MBA(A) 115 a theory paper or a lab, and how many credits does it carry?
MBA(A) 115 is a theory paper: Core, 2 lecture hours a week, 2 credits. Its practical side is a separate paper, MBA(A) 155 Data Preparation and Exploration - Lab, a Skill Enhancement lab with 2 practical hours and 1 credit. The official PDF bases the lab on MBA(A) 115, so the R code in these notes carries straight into it.
What are the passing marks in MBA(A) 115?
The official PDF prints internal assessment for MBA(A) 115 out of 25 marks: Class Test-I for 15 and a presentation, viva-voce or group discussion for 10. It does not print the end-term marks, the paper total or a pass percentage. The scheme follows Ordinance 11, which sets end-term minimums and re-appear rules, so read that ordinance on ipu.ac.in.
Which MBA(A) 115 unit has the most R code?
Units 2 and 4 lead with 8 R code examples each. Unit 2 works through cleaning and scaling functions such as duplicated(), gsub(), pmin() and scale(); Unit 4 runs kmeans(), hclust(), t.test(), chisq.test() and cor.test(). Unit 3 has 5 and Unit 1 has 4, for 25 in all.
Does the MBA(A) 115 syllabus on this page apply to my batch?
This page follows the MBA (Analytics) Scheme and Syllabus 2022-24 onwards, whose Semester 1 and 2 papers, MBA(A) 115 included, were approved by the Academic Council on 22.03.2023. If your institute hands you a newer syllabus, compare its MBA(A) 115 unit list with the coverage table above, or ask us on WhatsApp before you order.
Are the MBA(A) 115 long-answer questions solved in the notes?
The 24 short-answer questions, six per unit, are solved. The 28 long-answer questions are printed as "Practice Questions (10–15 Marks)" at the end of each unit, and each one matches a section of that unit, so you build the answer from that section, its table and its R example. The how-to-write section above shows the format.
Get the full MBA(A) 115 Data Preparation and Exploration Notes on WhatsApp
The MBA(A) 115 Data Preparation and Exploration IPU notes are a printed English book, not a PDF. Order on WhatsApp; delivery takes up to 5 to 7 days, depending on your location.
| Unit | Pages | R code examples |
|---|---|---|
| 1 Data Preparation | 5-18 (14) | 4 |
| 2 Data Pre-processing | 19-29 (11) | 8 |
| 3 Data Exploration | 30-41 (12) | 5 |
| 4 Data Illustration | 42-53 (12) | 8 |
| Book total | 54 (with cover and index) | 25 |
What the full MBA(A) 115 book contains, unit by unit
- Unit
- 1 Data Preparation
- Pages
- 5-18 (14)
- R code examples
- 4
- Unit
- 2 Data Pre-processing
- Pages
- 19-29 (11)
- R code examples
- 8
- Unit
- 3 Data Exploration
- Pages
- 30-41 (12)
- R code examples
- 5
- Unit
- 4 Data Illustration
- Pages
- 42-53 (12)
- R code examples
- 8
- Unit
- Book total
- Pages
- 54 (with cover and index)
- R code examples
- 25
Order the MBA(A) 115 notes book on WhatsApp (4 units, 54 pages)
Unnati Educations is an independent education provider based in Vikaspuri, Delhi. We are not affiliated with, authorised by, or endorsed by Guru Gobind Singh Indraprastha University (GGSIPU). 'GGSIPU' and 'IPU' are used only to describe the syllabus our notes follow. For official information, visit ipu.ac.in.
Ready for the full notes?
Discuss coverage and delivery with our team.