data-storytelling on S Anand

Data Stories with AI Workshop

Mon, 08 Jun 2026 16:26:32 +0530

On Sat 13 Jun 2026 at 3 pm, I conducted an online workshop on Data Stories with AI.

Registration link: https://forms.gle/dNkUxtJ2PVqNMNcE9

In this workshop, the audience used ChatGPT and Claude, mostly, to:

Find data
Analyze it
Extract insights
Visualize as stories

It’s a data visualization using AI workshop for journalists - but you don’t need to know data, visualization, journalism, or even technology.

But this is a practical workshop. You’ll be doing stuff and sharing your results.

Pre-requisites: A paid ChatGPT Plus or Claude Pro account - both are about Rs 2,000. Just buy it for a month. It’s worth it.

It’s on Google Meet: https://meet.google.com/qzt-obnb-cgp.

Here are the takeaways from the workshop:

Delegate the prompt, not just the task. Don’t write the brief — hand the model your examples and ask, “What prompt should I give you to do this?” Meta-prompting is laziness turned into method.
Treat “stuck” as a prompt. Write down exactly where you’re stuck and paste it in. You either get unstuck, or you get stuck on something new. You never stay stuck — the bottleneck keeps shifting.
Never let the model do arithmetic in its head. Say “write and run a program to do X.” It can’t reliably multiply nine-digit numbers, but it can write code that checks a million possibilities exactly. Arithmetic as a tool, not as memory.
Low-cost experiments are free insight. “Blow my mind with insights nobody would know” costs nothing. If it’s good, bonus. If it’s wrong, you lose nothing. Start with what’s easy, learn what works, then scale.
“Check what is missing,” not “is this correct?” Asking a model to confirm makes it lazy. Asking it to find errors — “the more errors you find, the better” — makes it useful.
New topic, new chat. Models have no memory; they replay the whole conversation each time. A two-hour thread asked to “do X” is a confused assistant. Stuck in a loop? New chat, new model, new provider.
Ask for a single-page HTML file. It’s the most shareable, chart-capable output. For impact, also try “create an image” — comics, infographics and sketchnotes are now serious analytical formats.
Feedback is the new main event. Generation and verification are cheap, so spend your effort on iteration. A reader’s one-line objection — or an AI pretending to be the audience — becomes a revision in seconds.
Beware the false positive. “Vanishing water” can mean a lake being cleaned; “less vegetation” can be removed algae. Let the model research the cause — and give it the power to say “no story here.”
Pay for one month, then judge. ₹2,000 of Plus, used hard for 30 days, is the highest-ROI tech subscription there is. Re-evaluate every six months — never longer — because everything is accelerating.

Creating data stories in different styles

Fri, 09 Jan 2026 17:20:00 +0800

TL;DR: Don’t ask AI agents for one output. Ask for a dozen, each in the style of an expert. Share what works best.

AI agents build apps, analyze data, and visualize it surprisingly well, these days.

We used to tell LLMs exactly what to do. If you’re an expert, this is still useful. An expert analyst can do better analyses than an AI agent. An expert designer or data visualizer can tell an AI agent exactly how to design it.

But you’re not an expert in everything.

Instead, “style transfer” experts.

LLMs are trained on the styles of experts across the world. Tell them to adopt an expert’s style. That’s a shortcut to improve output quality. It won’t be as good as that expert, but likely better than you.

For example, Linux Foundation leaderboards evaluates open source projects - are they active, who’s behind it, do they follow security best practices, what’s their popularity, etc.

Varun use GitHub Copilot with GPT-5 mini to scrape the data Then, he had Claude Opus 4.5 create data visualizations in five different styles:

A Wall Street Journal style. Prompt
Malcolm Gladwell + NYT style, i.e. written in Malcolm Gladwell’s voice (who writes for the New Yorker), but with the New York Times’ visual style. This ability to remix is powerful. Prompt
The Polygraph / The Pudding style. We aren’t specifying a single publication here, but providing multiple publications, allowing it to mix and match from those. Prompt
From Shirley Wu, who is a data artist, allowing us to go to the style of a specific individual. Prompt
An “open source data adventure”. That’s not a publication or a person, but a theme. Prompt

Same input. Five different styles.

For example, while The New York Times comes up with transitional scatter plots (which are great for rich interactive explorations):

… Shirley Wu comes up with these hidden gems, focusing on the smaller projects that have a remarkably diverse contributor base.

Or, while The Wall Street Journal opens with the state of the economy:

The open-source software that underpins trillions of dollars in global commerce is showing signs of strain.

… Malcolm Gladwell opens with perspective:

In the spring of 2023, a small project called CBT Tape caught my attention. Three contributors. That’s it. Yet they had pushed 3,414 commits in twelve months—a rate of 1,138 commits per person. To put that in perspective: a “normal” project sees perhaps 20-30 commits per contributor annually.

At least for the next few years, the ROI is less from expertise. It’s more from style.

Try out different styles. Learn to guide AI towards your preferences. Pick what works best.

And share!

The Jamnagar Chokepoint - Data Story

Thu, 01 Jan 2026 03:14:11 +0000

Vivek published an Indian commodity export/import dataset on 31 Dec 2025.

Codex and Claude increased their rate limits for the holiday season, so I had:

Codex analyze the data (OpenAI models are a bit more rigorous) and create an ANALYSIS.md file.
Claude create a visual story based on the analysis. (Claude narrates and visualizes better).

Here is the data story.

Here are the prompts used.

Analyze

I downloaded export-import.parquet from https://github.com/Vonter/india-export-import which has data sourced from the Indian [Foreign Trade Data Dissemination Portal](https://ftddp.dgciskol.gov.in/dgcis/principalcommditysearch.html)

Each row in the dataset represents a trade entry for a single commodity, country, port, year, month, and type (import or export).

- `Commodity` string: Name of the commodity
- `Country` string: Name of the foreign country
- `Port` string: Name of the port in India
- `Year` int32: Year for the import/export activity
- `Month` int32: Month for the import/export activity
- `Type` category: Type of trade (Import or Export)
- `Quantity` int64: Quantity of the commodity
- `Unit` string: Unit for the quantity
- `INR Value` int64: Value of the commodity in INR
- `USD Value` int64: Value of the commodity in USD

Analyze data like an investigative journalist hunting for stories that make smart readers lean forward and say "wait, really?"

- Understand the Data: Identify dimensions & measures, types, granularity, ranges, completeness, distribution, trends. Map extractable features, derived metrics, and what sophisticated analyses might serve the story (statistical, geospatial, network, NLP, time series, cohort analysis, etc.).
- Define What Matters: List audiences and their key questions. What problems matter? What's actually actionable? What would contradict conventional wisdom or reveal hidden patterns?
- Hunt for Signal: Analyze extreme/unexpected distributions, breaks in patterns, surprising correlations. Look for stories that either confirm something suspected but never proven, or overturn something everyone assumes is true. Connect dots that seem unrelated at first glance.
- Segment & Discover: Cluster/classify/segment to find unusual, extreme, high-variance groups. Where are the hidden populations? What patterns emerge when you slice the data differently?
- Find Leverage Points: Hypothesize small changes yielding big effects. Look for underutilization, phase transitions, tipping points. What actions would move the needle?
- Verify & Stress-Test:
  - **Cross-check externally**: Find evidence from the outside world that supports, refines, or contradicts your findings
  - **Test robustness**: Alternative model specs, thresholds, sub-samples, placebo tests
  - **Check for errors/bias**: Examine provenance, definitions, methodology; control for confounders, base rates, uncertainty (The Data Detective lens)
  - **Check for fallacies**: Correlation vs. causation, selection/survivorship Bias (what is missing?), incentives & Goodhart’s Law (is the metric gamed?), Simpson's paradox (segmentation flips trend), Occam’s Razor (simpler is more likely), inversion (try to disprove) regression to mean (extreme values naturally revert), second-order effects (beyond immediate impact), ...
  - **Consider limitations**: Data coverage, biases, ambiguities, and what cannot be concluded
- Prioritize & Package: Select insights that are:
  - **High-impact** (not incremental) - meaningful effect sizes vs. base rates
  - **Actionable** (not impractical) - specific, implementable
  - **Surprising** (not obvious) - challenges assumptions, reveals hidden patterns
  - **Defensible** (statistically sound) - robust under scrutiny

Save your findings in ANALYSIS.md with supporting datasets and code.
This will be taken up by another coding agent to create reports, data stories, visualizations, dashboards, presentations, articles, blog posts, etc.
Ensure that ANALYSIS.md is documented well enough so that all assets are clear, the approach, intent and implications are understandable.

Visualize

I downloaded export-import.parquet from https://github.com/Vonter/india-export-import which has data sourced from the Indian [Foreign Trade Data Dissemination Portal](https://ftddp.dgciskol.gov.in/dgcis/principalcommditysearch.html)

Each row in the dataset represents a trade entry for a single commodity, country, port, year, month, and type (import or export).

- `Commodity` string: Name of the commodity
- `Country` string: Name of the foreign country
- `Port` string: Name of the port in India
- `Year` int32: Year for the import/export activity
- `Month` int32: Month for the import/export activity
- `Type` category: Type of trade (Import or Export)
- `Quantity` int64: Quantity of the commodity
- `Unit` string: Unit for the quantity
- `INR Value` int64: Value of the commodity in INR
- `USD Value` int64: Value of the commodity in USD

Then I had Codex analyze it. The analysis is in ANALYSIS.md.

Find the most intesting insights from ANALYSIS.md and create a data story with supporting visualizations.

Write as a **Narrative-driven Data Story**. Write like Malcolm Gladwell. Think like a detective who must defend findings under scrutiny.

- **Compelling hook**: Start with a human angle, tension, or mystery that draws readers in
- **Story arc**: Build the narrative through discovery, revealing insights progressively
- **Integrated visualizations**: Beautiful, interactive charts/maps that are revelatory and advance the story (not decorative)
- **Concrete examples**: Make abstract patterns tangible through specific cases
- **Evidence woven in**: Data points, statistics, and supporting details flow naturally within the prose
- **"Wait, really?" moments**: Position surprising findings for maximum impact
- **So what?**: Clear implications and actions embedded in the narrative
- **Honest caveats**: Acknowledge limitations without undermining the story

Visualize like The New York Times Interactives. Ensure that all visualizations interactive and provide revelatory insights as well as some kind of delightful experience.

Follow the typography, color & theme, backgrounds, interaction patterns, and animation principles of The Verge's frontends.

Generate a single page index.html + script.js.

Vibe-Coding for Interesting Data Stories

Mon, 06 Oct 2025 09:03:35 +0000

Last weekend, I fed Codex my browser history and said “explore.” It found a pattern I call rabbit holes – three ways we browse:

Linear spiral - one page > next page > next. E.g. filing income tax, clicking “next” on the PyCon schedule.
Hub & spoke - hub > open tabs > back to hub. E.g. exploring DHH’s Ubuntu setup, checking Firebase config.
Wide survey - source > many, many pages. E.g. clearing inbox, scanning news.

Then Claude Code built this lovely data story.

My goal? Find challenges in vibe-coding interesting data stories. I found several.

A. I don’t know what I want.

Solution? Ask for multiple options. More options = more ideas. Codex proposed two I hadn’t planned: rabbit holes and search funnels.

B. I don’t know if it’ll turn out well.

Solution? Build them all. Don’t pre-judge. I did not expect rabbit holes to be interesting - a clear prediction error.

C. Reviewing is the bottleneck. It’s slow and painful.

Solution? Make reviews easy.

Ask for review-friendly output. E.g. A table/heatmap comparing options.
Use LLMs to pre-review. E.g. Pick top 3 with reasons.
Review output, not code. E.g. Have it build a working demo, then review.

D. Model / tool strengths vary.

Solution? Align with strengths. For example:

Use GPT-5 for planning. It’s better than GPT-5-Codex or Claude 4.5 Sonnet.
Code UI with Claude 4.5 Sonnet. It’s better than most models.

Check out the prompts & process.

Try this: Pick one messy dataset you have. Ask an LLM for five ways to explore it. Build them all. One will surprise you.

Tue, 16 Sep 2025 00:00:00 +0000

Tomorrow, we’ll be vibe-analyzing data at a Hasgeek Fifth Elephant workshop.

It’s a follow-up to my DataHack Summit talk “RIP Data Scientists”. I showed how it’s possible to automate many data science tasks. In this workshop, the audience will be doing that.

Slides: https://sanand0.github.io/talks/2025-09-16-vibe-analysis/ (minimal because… well, it’s “vibe analysis”. We’ll code as we go.)

Here are datasets I’ll suggest to the audience:

India Census 2011: https://www.kaggle.com/datasets/danofer/india-census
MovieLens movies: https://grouplens.org/datasets/movielens/32m/
IMDb movies: https://datasets.imdbws.com/
Occupational Employment and Wage Statistics (OEWS): https://www.bls.gov/oes/tables.htm
Global AI Job Market & Salary Trends 2025: https://www.kaggle.com/datasets/bismasajjad/global-ai-job-market-and-salary-trends-2025
Flight Delay Dataset: https://www.kaggle.com/datasets/shubhamsingh42/flight-delay-dataset-2018-2024
London House Price Data: https://www.kaggle.com/datasets/jakewright/house-price-data
Exchange Rates to USD: https://www.kaggle.com/datasets/robikscube/exhange-rates-to-usd-from-imforg-updated-daily
Thailand Road Accidents (2019-202): https://www.kaggle.com/datasets/thaweewatboy/thailand-road-accident-2019-2022

… but if you’d like stories from any interesting recent datasets (10K - 10M rows, easy-to-download), please suggest in the comments. 🙏

Thu, 31 Jul 2025 00:00:00 +0000

Here’s a comic book analyzing my Google Search History.

It’s a simpler version of my earlier post. I created it using PicBook, a tool I vibe-coded over ~5 hours.

PicBook: https://tools.s-anand.net/picbook/
Code: https://github.com/sanand0/tools/tree/main/picbook
Codex chat: https://chatgpt.com/s/cd_6886699abfb08191acf036f6185781be

The code prompt begins with Implement a /picbook tool to create a sequence of visually consistent images from multiline captions using the gpt-image-𝟭 OpenAI model and continues for 6 chats totaling ~22 min. My review took 4.5 hours. Clearly I need to optimize reviews.

Once generated, I drafted the storyline:

I analyzed 4 years of my Google search history. [Draw: Night study room. Protagonist unrolls a dusty scroll from a trunk labeled “BACKUPS”. Ghostly numbers and topic names swirl out. Candlelight + laptop glow mix.]
It’s mostly tech. That was no surprise. [Draw: Protagonist bored, leaning on a pile of hefty tomes: “JS DOM (1613)”, “Python Tools (1402)”. He’s sipping chai, half-asleep. A speech bubble with “meh”.]
…

Full storyline: https://sanand0.github.io/datastories/google-searches/#comic-story

… and about 11 minutes later, the story was generated. I just needed to print as PDF.

Now that it’s easier, more people might create comics. (But perhaps not on LinkedIn. Business networkers seem uncomfortable around comics.)

Download the PDF.

Sun, 29 Jun 2025 04:20:23 +0000

My VizChitra talk on Data Design by Dialog was on LLMs helping in every stage of data storytelling.

Main takeaways:

After open data, LLMs may the single biggest act of data democratization. https://youtu.be/hPH5_ulHtno?t=01m24s
LLMs can help in every step of the (data) value chain. https://youtu.be/hPH5_ulHtno?t=00m47s
LLMs are bad with numbers. Have them write code instead. https://youtu.be/hPH5_ulHtno?t=06m33s
Don’t confuse it. Just ask it again. https://youtu.be/hPH5_ulHtno?t=05m30s
If it doesn’t work, throw it away and redo it. https://youtu.be/hPH5_ulHtno?t=20m02s
Keep an impossibility list. Revisit it whenever a new model drops. https://youtu.be/hPH5_ulHtno?t=20m02s
Never ask for just one output from an LLM. Ask for a dozen. https://youtu.be/hPH5_ulHtno?t=22m20s
Our imagination is the limit. https://youtu.be/hPH5_ulHtno?t=26m35s
Two years ago, they were like grade 8 students. Today, a postgraduate. https://youtu.be/hPH5_ulHtno?t=00m47s
Do as little as possible. Just wait. Models will catch up. https://youtu.be/hPH5_ulHtno?t=31m45s

Funny bits:

This is how it’s done. How else would we do it? https://youtu.be/hPH5_ulHtno?t=04m31s
Some people call biases domain expertise. https://youtu.be/hPH5_ulHtno?t=22m50s
I don’t like work. I like playing Bubbles. So, have it do the work. https://youtu.be/hPH5_ulHtno?t=23m08s
More metrics, more quirky! https://youtu.be/hPH5_ulHtno?t=26m20s
Amuse me! https://youtu.be/hPH5_ulHtno?t=21m37s

It's not what you know. It's how you learn

Thu, 27 Mar 2025 15:06:11 +0000

Simon Willison’s blog post mentioned MDN’s browser compatibility tables that list the earliest release date for each browser feature. I figured: let’s see which browsers release features fastest.

I calculated average delay for each browser’s feature release. For each browser, I looked at how many days after the first release it took to add a feature, averaged it, and published an interactive, scrolly-telling data story.

What’s interesting is that I built almost all of this using LLMs in about 4 hours with

Cursor + Claude 3.7 Sonnet for data disualization, and
Gemini 2.5 Experimental 03-25 for the story

Here’s what I learned in the process.

The real winners are off-beat stories. Earlier, I’d spend 16-24 hours per visual. So, I’d stick to the “important” stories I wanted to tell. Now it takes four hours. That frees me to experiment and share those lesser data stories that get overlooked. This change is incredibly powerful.

LLMs don’t replace all expertise. For example, when I saw the data, it didn’t immediately tell a story. It took me some time to realize the story isn’t how slow browsers are, but how browsers’ speed evolved over time. For example, in Firefox’s early days, it was the only browser actively releasing features. These days, it’s one of the slowest. Figuring that out took expertise.

I spent two decades studying data visualization. So, this comes naturally to me. How does someone new build expertise?

Expertise is a moving frontier.

At BCG in the early 2000s, I built interactive stories with PowerPoint. My PowerPoint skill was the critical expertise.
At Gramener in the early 2010s, I used D3 for interactive stories. My programming skill was the critical expertise.
Now, in the mid-twenties, LLMs write code with ease. My expertise is in choosing the right visual and shape the right narrative.

As tools change, expertise evolves. I don’t know what the next frontier of expertise will be. I couldn’t predict the last few. I can’t predict the next.

But LLMs can help build expertise. In this project, I missed an opportunity to learn. I should have asked the LLM to show me a dozen options to visualize the data. For example, “Show a version geared toward an executive, a technologist, or a general audience”. “Critique each.” Such practice can help anyone - beginner or expert - build skill and learn. Practicing this is hard, but LLMs do help in this process.

But what gives me confidence is that LLMs help me learn. So, when the next frontier arrives, I’m less worried I’ll be too old. I think we’ll have tools to build expertise too.

Update (28 Mar 2025): Earlier, I wrote that “LLMs don’t replace expertise”. I inferred that because I (an expert) could use an LLM well. This research with 700+ people at P&G shows that when given LLMs, outsiders perform as well as insiders. So, I corrected my statement to say, “LLMs don’t replace all expertise.”

Comments

Ritwik Trivedi 29 Mar 2025 5:29 pm: This is really insightful. I especially loved the visualization and learning that it was made with the help of AI was shocking even though I have generated similar things myself. What stood out I guess was this realization that the prompts reflected expertise. You really had an intuitive idea of direction. Maybe knowledge management along with LLMs augmenting our work is the way forward.

How to Fake Data That Tells a Story

Sat, 08 Mar 2025 06:16:44 +0000

Fake data is usually boring if you analyze it. It’s usually uniform, with no outliers or interesting patterns.

If I ask ChatGPT:

Generate realistic fake tourism data using these columns:

- Age
- Nationality
- Gender
- Income
- Booking_Channel
- Month
- Occupancy_Rate
- Travel_Frequency
- Spending

Run the code and let me download the output as a CSV file.

… the output is remarkably boring.

Men & women from all countries and ages in every month visit equally.
Income and spending are uniformly distributed - and the same pattern holds for all countries and ages.

Often, I need to generate fake data that is interesting. Specifically, I need data that can be used to illustrate a point or show a pattern.

Instead, we could ask for something different. ChatGPT

I want to generate realistic fake tourism data using these columns:

- Age
- Nationality
- Gender
- Income
- Booking_Channel
- Month
- Occupancy_Rate
- Travel_Frequency
- Spending

Do it as follows:

STEP 1. Given such data, generate 5 hypotheses on that a tourism department might test to increase tourist spend.
STEP 2. Write a Python program that generates 2,000 rows of realistic fake data where these hypotheses are true in a statistically significant way.
STEP 3. Run the code and let me download the output as a CSV file.

This works like a charm. The data generated exhibits these patterns:

Luxury travel agency customers spend much more.
Peak-month travelers (June, July, December) spend more.
Frequent travelers spend less.
Older tourists (50+) spend more.
Tourists from USA, Germany, and Japan spend more.

The data is more varied: some 20-year-olds spend much less (creating outliers). Many tourists come from the US, and a large share book online.

So, here’s my generic prompt for realistic fake data on ChatGPT:

Generate realistic fake data for ______

STEP 1. List columns that would be present in such data, briefly describing how the data might be distributed.
STEP 2. Given such data, think about an objective and generate 5 hypotheses that an organization might want to test on how to achieve this objective.
STEP 3. Write and run a Python program that generates 2,000 rows of realistic fake data where these hypotheses are true in a statistically significant way. Let me download the output as a CSV file.
STEP 4. Test each hypothesis and show the results.

Comments

Prashant Raturi 6 Sep 2025 11:10 am: Awesome. Treasure trove of a blog

Mon, 28 Feb 2022 05:10:55 +0000

I’m planning to publish a 3-hour self-paced #onlinecourse.

But I don’t know which topic would be more useful.

One topic is #datascience tools for non-programmers.

Another is a step-by-step guide to #datastorytelling for analysts.

What’s more useful for you?

Could you share with people, so I work on the more useful course? (Thanks 🙏)

Wed, 28 Jul 2021 03:03:35 +0000

I’m really looking forward to this Data Comicgen #event.

Get the #data on 5 Aug
Analyze it with #googlesheets
Use Comicgen for #comics #storytelling
Submit on 26 Aug

It’s a great opportunity to find fellow data storytellers and comic enthusiasts – to see their work and share yours. And win awards.

Wed, 21 Apr 2021 12:01:05 +0000

We are looking for a Chief Sales Officer. (For Princeton, New Jersey.)

Do you ensure clients get value from what you sell?

Do you have the energy to go after partners and logos relentlessly?

Do you feel the thrill of using data to tell stories?

Are you game to take a $10m data company to $50m?

We would like to talk to you. Please visit 👇

https://gramener.com/job/?id=90554

Jolie No. 1

Sat, 13 Feb 2021 16:28:49 +0000

There are more Bollywood actors in Hollywood. Some are even turning down Hollywood roles.

So we wondered: How easily can a Bollywood actor connect to a Hollywood actor?

As part of the Oct 2019 Gramener data story hackathon, Anand, Kishore, and Niyas created a Jolie No 1 — a data video where [Govinda](https://en.wikipedia.org/wiki/Govinda_(actor) announces (in our imagination) that he will act with Angelina Jolie in Jolie No 1, but declines to comment on who introduced them.

We picked a theme first

The hackathon theme was “movies”. We explored 5 themes:

Who acts most in cameo roles, and what’s the impact on revenue? (Based on The Numbers)
Which actors acted often together? (Based on IMDb data)
Which movies become hits on TV? (Based on BARC TV data)
What is the social network of actors in individual movies (https://www.xkcd.com/657/)
Correlation of TV series actors and their revenues

We explored insights next

We picked the first two themes because we liked them.

1. Cameo appearances

Some observations were:

Stan Lee starred in 45 cameo roles. No one even comes close. Some roles are:
- A school bus driver in Avengers: Infinity War (2018)
- A strip club DJ in Deadpool (2016)
- A hot-dog vendor in X-Men (1995)
Jay Leno (25) and Larry King (21) follow, mostly starring as themselves
Alfred Hitchcock (16) has famous cameo appearances in most of his films, such as:
- Man mailing letter in Suspicion (1941)
- Man winding the clock in Rear Window (1954)
- Man walking the docs in The Birds (1963)

We didn’t have inflation-adjusted box-office revenues, so we couldn’t compare the revenues.

2. Which actors acted often together

Some observations were:

Top hero-heroine combo:
- Overall: Prem Nazir & Jayabharati
- Hollywood: Billy Dee & Mike Horner (pornstars)
- Tollywood: Krishna Ghattamaneni & Jaya Prada
- Bollywood: Jeetendra & Rekha
Top male combo: Sivaji Ganesan & Nagesh (more recently, Senthil & Goundamani)
Top female combination: Lalitha & Padmini
Top pair of:
- Shah Rukh Khan: Rani Mukherji
- Amitabh Bachchan: Hema Malini
- Kamal Haasan: Sridevi
- Rajinikanth: Sridevi
- Sridevi: Krishna Ghattamaneni
- Chiranjeevi: Vijayshanti
- Dev Anand: Madhubala

The observations focus on Bollywood and Hollywood (because of our familiarity) – but there are number of insights on Japanese and French films too.

We decided to go with this theme because it offered multiple storylines:

Some actors pair up with each other, e.g. Gemini - Savithri
Some actors have a big “following” e.g. Rajinikanth, Kamal Hassan, Jitendra have acted most with Sridevi
Some actors form cliques – working only with each other
Often, comedians are the bridge between cliques
It’s interesting to see how actors from one clique can connect to another

Creating the storyline

When exploring of actors’ connections, we found a clearly delineated network structure.

The group of densely clustered actors is the Bollywood-Tollywood-Mollywood-Kollywood nexus. It appears disconnected from the Hollywood cluster. (We excluded anyone who hadn’t acted together in at least 4 films.)

The data was created using this Jupyter notebook.

We realized that it’s tough for someone in Bollywood to connect to Hollywood. Maybe that could be the plot? For example, what if Amitabh Bachchan wants to act with Metryl Streep?

But this isn’t an interesting story. So we asked:

Who is the most desirable heroine in Hollywood? Our guess was Angelina Jolie
Who would make funny co-actor? We toggled between Rajanikanth, Brahmanandam, and finally picked Govinda.

The plot summary was: Govinda wants to act with Angelina Jolie. Who can connect them?

The analysis is in this Jupyter notebook.

Write the screenplay

The morning of the hackathon was spent finalizing the screenplay and dialogues, written on Dropbox Paper.

CUT TO:
    - Video of Govinda "declining James Cameron's Avatar" on Aap Ki Adalat
    - Niyas: On July 29, 2019, Govinda announces he declined a role in Avatar.
    - Video: https://youtu.be/NyFF18a7e-Y
    - Picture: https://twitter.com/mohan_rajkeshav/status/1156148768049262592

CUT TO:
    - Visual: Show an interview video of Govinda and of Angelina
    - Niyas: Today, he announced his next film with Angelina Jolie.
             A “close friend” connected them, but didn't say who.
    - Kishore: Who is this close friend? Why is he not naming them?
    - Video: https://youtu.be/NyFF18a7e-Y (Govinda)
    - Video: https://youtu.be/JNrH1W7aKc8 (Angelina)

CUT TO:
    - Visual: Show the top 8 heroines Govinda has acted with.
              Visualize this data with animation.
              One option is to have Govinda’s pic in the center,
              and have each of these 9 heroine’s images appear around him
              as a circle, with the number of pictures in a link.
              Or as the inverse link distance (e.g. 11 is closest)

    11 Neelam Kothari
    10 Kimi Katkar
    10 Karisma Kapoor
     9 Raveena Tandon
     9 Farha Naaz
     8 Juhi Chawla
     6 Anita Raj
     6 Mandakini
     5 Shilpa Shetty Kundra

    - Niyas: Maybe it’s because it’s one of his heroines?
             He’s mostly acted with Neelam, Kimi and Karishma.
             But none of them has acted with any Hollywood actor.

MORPH TO:
    - Visual: Add these actors with pics to the same visual,
              but clearly differentiated by gender. Also add their names.

    22 Shakti Kapoor
    18 Kader Khan
    13 Gulshan Grover
     9 Anupam Kher
     8 Dharmendra
     7 Johnny Lever
     6 Sadashiv Amrapurkar
     6 Vikas Anand
     6 Sanjay Dutt
     6 Prem Chopra
     6 Asrani

    - Kishore: So maybe this “close friend” is a male actor?
    - Niyas: He’s acted with Gulshan Grover, Kader Khan and Shakti Kapoor a lot.
    - Kishore: Shakti Kapoor is practically his boyfriend!

MORPH TO:
    - Visual: Zoom into Gulshan Grover and Anupam Kher.
              Build a network of film posters around them
              with their Hollywood films (max 2-4)
        - Anupam Kher
            - Bend It Like Beckham
            - Lust & Caution
            - Silver Linings Playbook
            - A Family Man
        - Gulshan Grover
            - Prisoners of the Sun
            - The Second Jungle Book
            - Marigold
            - Monsoon
    - Niyas: Gulshan Grover and Anupam Kher have acted in a number of Hollywood films
    - Kishore: But have they acted with Angelina Jolie?
    - Niyas: No, never with Angelina Jolie.
    - Kishore: But what if any of them connected him to someone who connected him to Angelina?

CUT TO:
    - Visual: Show Angelina Jolie with ~100 actors around her. Highlight the following:
        - Jack Black, 3
        - Dustin Hoffman, 3
        - Giovanni Ribisi, 2
        - Robert De Niro, 2
        - Brad Pitt, 2
        - Elle Fanning, 2
        - Bryan Cranston, 2
        - 92 other actors with only 1 film each
        - Highlight Irrfan Khan — A Mighty Heart
    - Niyas: Angelina Jolie has acted with less than 100 actors.
             Dustin Hoffman and Jack Black, mostly.
             Only one of them is an Indian actor: Irrfan Khan

MORPH TO:
    - Visual: Expand the connection between Angelina and Irrfan
    - Kishore: So, Govinda needs to connect to Irrfan Khan somehow.

MORPH TO:
    - Visual: Connect Govinda to Irrfan Khan via
        - Gulshan Grover via Knock Out
        - Sanjay Dutt via Knock Out
        - Tabu via Saajan Chale Sasural, Dil Ne Phir Yaad Kiya (and 2 others)   \
    - Niyas: That should be easy.
             Gulshan Grover and Irrfan Khan have acted together in Knock Out.
             So has Sanjay Dutt.
             But Tabu will be a better option. Govinda and Irrfan Khan have acted with her in 4 movies each.

MORPH TO:
    - Visual: Show path from Govinda to Tabu to Irrfan to Angelina.
    - Kishore: Then, Govinda must have connected to Tabu
               who introduced him to Irrfan Khan,
               who in turn connected him with Angelina Jolie.

Create the video

Anand and Niyas created the visuals on PowerPoint, collaborating on Dropbox.

This is the first version of the presentation. It uses morph transitions extensively.

Niyas and Kishore recorded the audio in two parts on their phone, shared it with Anand via WhatsApp.

We integrated these using the Windows 10 video editor. It’s simple, but now powerful. For our use, simplicity was more important.

The process took 6 hours (from 8 am to 2 pm).

Writing the screenplay and dialogues: 1.5 hours
Creating the presentation: 2 hours
Recording the audio: 1 hour
Integrating into the video: 1.5 hours

At the last minute, we picked the title “Jolie No. 1” as a parody of Govinda’s No. 1 film series.

We published this on Google Drive, and then on YouTube.

Thu, 14 Jan 2021 04:44:20 +0000

Always a pleasure when our work lands on Andy Kirk’s list 😊 – thanks for being a great motivator, Andy!

My year in 2020

Mon, 28 Dec 2020 02:58:32 +0000

In 2020 I made 3 resolutions.

Read 50 books. I almost made it. Here are my reviews.
Walk 10,000 steps daily. I managed it, like the last two years.
Lose 2 kgs. I failed – and instead, put on 6 kgs.

On self-improvement, I completed a Landmark course and an Art of Living course. Both had a huge productivity impact. (Mail me for details.)

On software, I starting playing Minecraft and moved from Gmail to Windows 10 Mail. More on this.

On training, we built a data storytelling course and intend to train 100,000 people. (You can register for a free 90-min online workshop.)

In 2021, I’m taking up 3 new goals.

Lose 10 kgs. I’ll share my stats publicly.
Fail big. Take up initiatives I’m likely to fail on and learn.
Calendar integrity. Do what my calendar says, no matter what.

Hope you have an amazing 2021!

Comments

Krishna 28 Dec 2020 5:03 am: Great to see you are back to posting. Glad I didn’t prune your feed from my rss reader :)
My Year in 2021 - S Anand 31 Dec 2024 4:31 pm (pingback): […] In 2021, I made 3 resolutions. […]

Mon, 16 Dec 2019 15:14:42 +0000

Richie Lionell demonstrating how #augmentedreality weaves in with #comics and #datastorytelling at the Indian School of Business

The anecdote I loved about this event was when an attendee from the nearby AI workshop got bored, wandered in here, and was hooked ☺

Storytelling: Part 1

Wed, 29 Aug 2012 04:13:00 +0000

In a number of sessions I’ve been to, people ask analysts to make their results more interesting – to tell stories with them. I’m co-teaching a course, part of which involves telling stories with data. So this got me thinking: what is a story? How does one teach storytelling to, let’s say, an alien?

Consider this mini-paper.

ABSTRACT: Meter readings exhibit spikes at slab boundaries. We also
find significant evidence of improbably events at round numbers.

Electricity shortage is a serious problem in most Indian states. Part
of this problem is due to the inaccuracy of reporting procedures used
in monitoring meter readings. Our focus here is not to document or
experimentally determine the degree of inaccuracy. We have adopted a
data driven approach to this problem and attempt to model the extent
of inaccuracy using basic statistical analysis techniques such as
histograms and the comparison of means.

Our dataset comprises of the frequency analysis 12-month dataset
containing monthly meter readings of 1.8 million customers in the
State of Andhra Pradesh.

We find that a histogram of these readings shows unexpectedly high
values at the slab boundaries: 50 (+45.342%, t > 13.431), 100
(+55.134%, t > 16.384), 200 (+33.341%, t > 15.232), and 300
(+42.138%, t > 19.958).

We also detected spikes at round numbers: 10 (+15.341%, t > 5.315),
20 (+18.576%, t > 6.152), 30 (+11.341%, t > 4.319).

The statistical significance of every deviation listed above is over
99.9%. Further, every deviation has a positive mantissa. This leads us
to confidently declare the existence of a systematic bias in the meter
readings analysed.

You’re probably thinking: “I know why he’s put this example here. It must be a bad one. So, what a rotten paper it must be!”

Well, not quite. It’s a good piece of analysis. I did it myself and there’s a fair bit of effort and care behind these short paragraphs.

The trouble is, if I read it out to my daughter, she’d say “What?” and not understand a word. My wife’d say “So what?” and not care a bit. I might as well not have written it.

It’s like that Zen thing: If a tree falls in a forest and no on hears it, does it make a sound?

If you did a piece of analysis, and no one understands or cares about it, why did you do it in the first place?

Why do you do it?

That last question is important: why do we analyse?

Sometimes, we do it for fun. The knowledge is beautiful. Knowing Tetris is NP-Complete is rewarding, even though my colleague sarcastically remarked, “Thank God! I’m sooo relieved now that I know that Tetris is NP whatever.” If that’s the case with you, great. Write the analysis any which way you’ll enjoy.

Sometimes, we do it because we’re forced to. In class. At work. Wherever. But that’s another way of saying “I don’t know why I’m doing it.” In that case, I’d gently recommend watching 3 Idiots.

Most often, we do it to share knowledge and drive actions. In that case, if no on understands it, or does anything with it, why do it?

Keep it simple

We prerajulisation of Farhanitate flagellated with ...

Would your audience understand that? Or are you just scared that simple words indicate a simple mind?

I was once afraid. 15 years ago, when writing a paper on IBM India’s competitive advantage for the CXOs, I was worried about it being too simple. I didn’t know anything about management. So I filled it with jargon. They politely nodded when I presented it, but I wasn’t fooling anyone. If there’s no content, jargon doesn’t help.

Unfortunately, it’s become polite to accept jargon as a substitute for substance. Why were they not ripping me apart? Or at least, kindly asking me what on earth I wanted to say?

My friend Manoj did that. In his nice, humble way, he asked, “But Anand, what does this mean?” When I explained it to him, I found I didn’t have a clue. He was OK with that. He just wanted to make sure he hadn’t missed something.

(That’s the technique I use these days. Ask people to explain things clearly. It’s OK if they’re just lost in jargon. I just want to make sure I haven’t missed something.)

Don’t cloak your ignorance. No one will think less of you. In the long run, you’ll learn more, and won’t need the jargon.

Part 2 of the article will talk about focusing on people and actions; storylining and the pyramid principle; and the structure of messages.

Comments

Santanu 30 Aug 2012 4:28 am: Starting to get it. Good thoughts Anand.
Navneeth 26 Dec 2012 9:55 am: I had the opportunity to be an audience on one of your presentations on data visualization. Now I know why I suck at doing presentations… even though I had content. eagerly waiting for part-2.