What Makes an App Go Viral?¶

Analyzing App Store and Google Play Data to Discover Winning App Profiles

  • Author: Chris Campbell
  • Date: 10/26/2025
  • GitHub: github.com/texasbe2trill

As data analysts for a mobile app development company, our mission is simple: help our developers create apps that people love — and use. Since our apps are free and rely on ad revenue, understanding what drives user engagement is key to growth.

In this project, we’ll dive into real-world app data from Google Play and the App Store to uncover what separates the most downloaded apps from the rest. By blending data cleaning, visualization, and exploratory analysis, we’ll highlight insights that can shape smarter design, marketing, and development strategies.

Dataset Description¶

This project uses two datasets containing detailed information about mobile applications from both the Apple App Store and the Google Play Store. Each dataset includes app-specific attributes such as name, category, rating, size, price, and user engagement metrics

By comparing patterns across both platforms, we aim to identify what types of apps tend to attract more users and maintain higher ratings.

The datasets allow us to:

  • Examine key characteristics that influence app popularity.
  • Compare free vs. paid apps and their relationship to user engagement.
  • Understand trends across categories, genres, and content ratings.
  • Provide actionable insights for developers to optimize future app releases.

📱 Apple App Store Dataset¶

Column Name Description
id App ID
track_name App Name
size_bytes Size (in Bytes)
currency Currency Type
price Price amount
rating_count_tot User Rating counts (for all versions)
rating_count_ver User Rating counts (for current version)
user_rating Average User Rating value (for all versions)
user_rating_ver Average User Rating value (for current version)
ver Latest version code
cont_rating Content Rating
prime_genre Primary Genre
sup_devices.num Number of supporting devices
ipadSc_urls.num Number of screenshots displayed for app preview
lang.num Number of supported languages
vpp_lic VPP Device-Based Licensing Enabled

🤖 Google Play Store Dataset¶

Column Name Description
App App Name
Category App Category
Rating Average User Rating
Reviews Number of User Reviews
Size Size of the App (Varies by Device)
Installs Number of User Installs
Type App Type (Free or Paid)
Price Price of the App
Content Rating Age Group Targeted
Genres App Genres
Last Updated Date of Last Update
Current Ver Current Version of the App
Android Ver Minimum Android Version Required

1) Load CSVs into Python Lists¶

  • Imports reader from Python’s built-in csv module.
  • Opens AppleStore.csv and googleplaystore.csv, creates CSV readers, then converts them to lists of lists:
    • apple_app_data → Apple App Store dataset.
    • google_play_data → Google Play Store dataset.
In [13]:
# Import reader from csv
from csv import reader

# Read in the App Store and Google Play datasets
open_app_store = open('data/AppleStore.csv')
read_app_store = reader(open_app_store)

open_google_play = open('data/googleplaystore.csv')
read_google_play = reader(open_google_play)


# Save app_store dataset as a list of lists
apple_app_data = list(read_app_store)

# Save google_play dataset as a list of lists
google_play_data = list(read_google_play)

2) Helper: explore_data(dataset, start, end, rows_and_columns=False)¶

  • Prints a slice of the dataset from start to end (row-by-row), inserting a blank line between rows.
  • If rows_and_columns=True, also prints:
    • Total number of rows (len(dataset)).
    • Number of columns (len(dataset[0])).
  • Useful for quick, readable peeks at data and shape.
In [14]:
# Explore each dataset
def explore_data(dataset, start, end, rows_and_columns=False):
    dataset_slice = dataset[start:end]    
    for row in dataset_slice:
        print(row)
        print('\n') # adds a new (empty) line after each row

    if rows_and_columns:
        print('Number of rows:', len(dataset))
        print('Number of columns:', len(dataset[0]))

3) Google Play: Inspect, Fix a Known Bad Row, and Check Duplicates¶

  • explore_data(google_play_data, 0, 5): displays the first five rows.
  • Prints row at inprint("The first five rows in the App Store dataset:") print('-' * 35) print('\n')dex 10473, a known problematic record (missing the Category field per Kaggle discussions).
  • Deletes that bad row with del google_play_data[10473], then prints the new row at 10473 to confirm removal.
  • Duplicate check (by app name):
    • Iterates through google_play_data and tracks app names (app[0] → App column).
    • Builds:
      • unique_android_apps: first occurrence of each app name.
      • duplicate_android_apps: subsequent occurrences (duplicates).
    • Reports how many duplicates were found and prints a sample.
In [15]:
# Explore Google Play data
print("The first five rows in the Google Play Store dataset:")
print('-' * 35)
print('\n')
explore_data(google_play_data, 0, 5) # Return the first five rows

# Check for error in row 10473 as noted in Kaggle discussion
print('-' * 35) # print a line to separate the output
print('\n')
print('The current row data for index position 10473:')
print('-' * 35)
print(google_play_data[10473])
print('\n')

# Row 10473 is missing data for the 'Category column'
# Remove row 10473 from the dataset
del google_play_data[10473]

# Check if the row was removed:
print('The new row at index position 10473 is:')
print('-' * 35)
print(google_play_data[10473])
print('\n')

# Check for duplicate apps
print('Duplicate Android Apps:')
print('-' * 35)
duplicate_android_apps = []
unique_android_apps = []

for app in google_play_data:
    name = app[0]
    if name in unique_android_apps:
        duplicate_android_apps.append(name)
        
    else:
        unique_android_apps.append(name)
        

# Print the number of duplicate apps in the google play dataset
if len(duplicate_android_apps) > 0:
    print(f'There are {len(duplicate_android_apps)} duplicate android apps.')
    print('\n')
    print('Example of duplicate android apps:', duplicate_android_apps[:15])
    
else:
    print(f'There are {len(duplicate_android_apps)} duplicate android apps.')

The first five rows in the Google Play Store dataset:
-----------------------------------


['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type', 'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver', 'Android Ver']


['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up']


['Coloring book moana', 'ART_AND_DESIGN', '3.9', '967', '14M', '500,000+', 'Free', '0', 'Everyone', 'Art & Design;Pretend Play', 'January 15, 2018', '2.0.0', '4.0.3 and up']


['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up']


['Sketch - Draw & Paint', 'ART_AND_DESIGN', '4.5', '215644', '25M', '50,000,000+', 'Free', '0', 'Teen', 'Art & Design', 'June 8, 2018', 'Varies with device', '4.2 and up']


-----------------------------------


The current row data for index position 10473:
-----------------------------------
['Life Made WI-Fi Touchscreen Photo Frame', '1.9', '19', '3.0M', '1,000+', 'Free', '0', 'Everyone', '', 'February 11, 2018', '1.0.19', '4.0 and up']


The new row at index position 10473 is:
-----------------------------------
['osmino Wi-Fi: free WiFi', 'TOOLS', '4.2', '134203', '4.1M', '10,000,000+', 'Free', '0', 'Everyone', 'Tools', 'August 7, 2018', '6.06.14', '4.4 and up']


Duplicate Android Apps:
-----------------------------------
There are 1181 duplicate android apps.


Example of duplicate android apps: ['Quick PDF Scanner + OCR FREE', 'Box', 'Google My Business', 'ZOOM Cloud Meetings', 'join.me - Simple Meetings', 'Box', 'Zenefits', 'Google Ads', 'Google My Business', 'Slack', 'FreshBooks Classic', 'Insightly CRM', 'QuickBooks Accounting: Invoicing & Expenses', 'HipChat - Chat Built for Teams', 'Xero Accounting Software']

4) Apple App Store: Inspect and Check Duplicates¶

  • explore_data(apple_app_data, 0, 5): displays the first five rows.
  • Duplicate check (by id):
    • Iterates through apple_app_data and tracks app[0] (the id column).
    • Builds:
      • unique_apple_apps: first occurrence of each app ID.
      • duplicate_apple_apps: subsequent occurrences (duplicates).
    • Reports how many duplicates were found and prints a sample.
  • 📝 Note: Apple duplicates are identified by App ID (more reliable than app name). On Google Play, duplicates are checked by App name.
In [16]:
# Explore App Store data
print("The first five rows in the App Store dataset:")
print('-' * 35)
print('\n')

explore_data(apple_app_data, 0, 5) # Return the first five rows

# Check for duplicate apps
duplicate_apple_apps = []
seen_ids = set()

for app in apple_app_data[1:]:
    app_id = app[0]
    name = app[1]
    if app_id in seen_ids:
        duplicate_apple_apps.append(app_id, name)
        
    else:
        seen_ids.add(app_id)
        
        
# Print the number of duplicate apps in the App Store dataset
print('Duplicate Apple Apps:')
print('-' * 35)

if len(duplicate_apple_apps) > 0:
    print(f'There are {len(duplicate_apple_apps)} duplicate apple apps.')
    print('\n')
    print('Example of duplicate apple apps:', duplicate_apple_apps[:15])
    
else:
    print(f'There are {len(duplicate_apple_apps)} duplicate apple apps.')

    

The first five rows in the App Store dataset:
-----------------------------------


['id', 'track_name', 'size_bytes', 'currency', 'price', 'rating_count_tot', 'rating_count_ver', 'user_rating', 'user_rating_ver', 'ver', 'cont_rating', 'prime_genre', 'sup_devices.num', 'ipadSc_urls.num', 'lang.num', 'vpp_lic']


['284882215', 'Facebook', '389879808', 'USD', '0.0', '2974676', '212', '3.5', '3.5', '95.0', '4+', 'Social Networking', '37', '1', '29', '1']


['389801252', 'Instagram', '113954816', 'USD', '0.0', '2161558', '1289', '4.5', '4.0', '10.23', '12+', 'Photo & Video', '37', '0', '29', '1']


['529479190', 'Clash of Clans', '116476928', 'USD', '0.0', '2130805', '579', '4.5', '4.5', '9.24.12', '9+', 'Games', '38', '5', '18', '1']


['420009108', 'Temple Run', '65921024', 'USD', '0.0', '1724546', '3842', '4.5', '4.0', '1.6.2', '9+', 'Games', '40', '5', '1', '1']


Duplicate Apple Apps:
-----------------------------------
There are 0 duplicate apple apps.

5) De-duplicating Google Play by Keeping the Most-Reviewed Entry¶

  • Goal: For each Android app name, keep only the record with the highest number of reviews (proxy for the most recent/most representative entry).
  • Creates a dictionary reviews_max mapping:
    • Key: app name (row[0]).
    • Value: maximum review count observed (float(row[3]) → Reviews column).
  • Logic:
    • Skip header (google_play_data[1:]).
    • If the app already exists in reviews_max and the current row’s n_reviews is larger, update it.
    • If not present, add it.
  • Prints the first five key–value pairs and the total number of unique apps captured in reviews_max.
  • ✅ This sets up a clean index to later rebuild a de-duplicated dataset named android_clean where each app appears once with its highest review count.
In [17]:
# Removing Duplicate Entries

reviews_max = {}

for row in google_play_data[1:]: # Exclude header row
    name = row[0]
    n_reviews = float(row[3])
    
    if name in reviews_max and reviews_max[name] < n_reviews:
        reviews_max[name] = n_reviews
        
    elif name not in reviews_max:
        reviews_max[name] = n_reviews
        
# Inspect the dictionary
print('The first five entries in the reviews_max dictionary:')
print('-' * 35)
for key, value in list(reviews_max.items())[:5]:
    print(f'| {key} | {value}')
    
print('\n')
print(f'The reviews_max dictionary has {len(reviews_max)} entries.')

# Remove the duplicate rows utilizing reviews_max dictionary
print('\n')
print('The first five rows of the android_clean dataset:')
print('-' * 35)
android_clean = []
already_added = []

for row in google_play_data[1:]:
    name = row[0]
    n_reviews = float(row[3])
    
    if n_reviews == reviews_max[name] and name not in already_added:
        android_clean.append(row)
        already_added.append(name)
        
        
# Explore the android_clean dataset
explore_data(android_clean, 0, 5)

print(f'The android_clean dataset has {len(android_clean)} entries.')

The first five entries in the reviews_max dictionary:
-----------------------------------
| Photo Editor & Candy Camera & Grid & ScrapBook | 159.0
| Coloring book moana | 974.0
| U Launcher Lite – FREE Live Cool Themes, Hide Apps | 87510.0
| Sketch - Draw & Paint | 215644.0
| Pixel Draw - Number Art Coloring Book | 967.0


The reviews_max dictionary has 9659 entries.


The first five rows of the android_clean dataset:
-----------------------------------
['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up']


['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up']


['Sketch - Draw & Paint', 'ART_AND_DESIGN', '4.5', '215644', '25M', '50,000,000+', 'Free', '0', 'Teen', 'Art & Design', 'June 8, 2018', 'Varies with device', '4.2 and up']


['Pixel Draw - Number Art Coloring Book', 'ART_AND_DESIGN', '4.3', '967', '2.8M', '100,000+', 'Free', '0', 'Everyone', 'Art & Design;Creativity', 'June 20, 2018', '1.1', '4.4 and up']


['Paper flowers instructions', 'ART_AND_DESIGN', '4.4', '167', '5.6M', '50,000+', 'Free', '0', 'Everyone', 'Art & Design', 'March 26, 2017', '1.0', '2.3 and up']


The android_clean dataset has 9659 entries.

Removing Non-English App Names (ASCII Heuristic)¶

What this cell does

  • Defines english_check(name), which returns True if an app name has 3 or fewer non-ASCII characters (characters with ord(ch) > 127), and False otherwise.
    • Rationale: Many English titles include a few special characters (™/®/—/emoji). Allowing up to 3 tolerates these without discarding genuinely English apps.
  • Applies this function to:
    • android_clean → produces android_english
    • apple_app_data[1:] (skips header) → produces ios_english
  • Uses explore_data(..., rows_and_columns=True) to preview a few rows and confirm the row/column counts of the filtered datasets.

Why it matters

  • Our analysis focuses on English-language apps to ensure consistent interpretation of text fields like Category, Genres, and user-facing titles.
  • Filtering reduces noise from multilingual titles that could skew counts or downstream text processing.

How the heuristic works

  1. Iterate each character in the app name.
  2. Count characters where ord(char) > 127.
  3. If the count exceeds 3, classify the name as non-English.

Caveats

  • This is a simple ASCII heuristic:
    • It may keep some non-English titles if they contain only a few non-ASCII characters.
    • It may exclude legitimate English titles with many symbols/emoji.
  • That trade-off is acceptable here to quickly narrow to mostly English apps without complex NLP.

Result (from the sample printout)

  • Android (English): example rows shown and dataset shape reported as 9,614 rows × 13 columns.
  • iOS (English): example rows shown and dataset shape reported as 7,197 rows × 16 columns.
In [18]:
# Removing Non-English Apps
def english_check(string):
    """
    This function checks if a string contains more than 3 non-English characters.
    It returns True if a string contains 3 or fewer 
    non-English characters, False otherwise.
    """
    non_english_count = 0
    for character in string:
        if ord(character) > 127:
            non_english_count += 1
            if non_english_count > 3:
                return False
    return True

#print(english_check('Instagram'))
#print(english_check('爱奇艺PPS -《欢乐颂2》电视剧热播'))
#print(english_check('Docs To Go™ Free Office Suite'))
#print(english_check('Instachat 😜'))

# Filter out non-English apps from android_clean dataset
android_english = []
for app in android_clean:
    name = app[0]
    
    if english_check(name):
        android_english.append(app)
        
# Filter out non-English apps from apple_app_data dataset
ios_english = []
for app in apple_app_data[1:]:
    name = app[0]
    
    if english_check(name):
        ios_english.append(app)

# Explore the filtered datasets
print("Android English Apps:")
explore_data(android_english, 0, 3, True)
print("\nIos English Apps:")
explore_data(ios_english, 0, 3, True)

Android English Apps:
['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up']


['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up']


['Sketch - Draw & Paint', 'ART_AND_DESIGN', '4.5', '215644', '25M', '50,000,000+', 'Free', '0', 'Teen', 'Art & Design', 'June 8, 2018', 'Varies with device', '4.2 and up']


Number of rows: 9614
Number of columns: 13

Ios English Apps:
['284882215', 'Facebook', '389879808', 'USD', '0.0', '2974676', '212', '3.5', '3.5', '95.0', '4+', 'Social Networking', '37', '1', '29', '1']


['389801252', 'Instagram', '113954816', 'USD', '0.0', '2161558', '1289', '4.5', '4.0', '10.23', '12+', 'Photo & Video', '37', '0', '29', '1']


['529479190', 'Clash of Clans', '116476928', 'USD', '0.0', '2130805', '579', '4.5', '4.5', '9.24.12', '9+', 'Games', '38', '5', '18', '1']


Number of rows: 7197
Number of columns: 16

Isolating Free Apps (Android & iOS)¶

What this cell does

  • From the English-only datasets, it builds two subsets:
    • free_android_apps: rows from android_english where the Price field equals '0' or '0.0'.
    • free_ios_apps: rows from ios_english where the price field equals '0' or '0.0' (USD).
  • Prints a small preview and the shape (rows × columns) of each filtered dataset.

How it identifies “free”

  • Android (Google Play)
    Uses price = app[-6] (the Price column) and keeps rows where price is '0' or '0.0'.

    Note: In the Google Play CSV, Type may say Free, but Price is the reliable numeric flag (0 for free).

  • iOS (App Store)
    Uses price = app[4] (the price column) and keeps rows where price is '0' or '0.0'.

Why this matters

  • Our business model relies on ad-supported free apps. Filtering to free titles lets us analyze categories, ratings, and installs that directly affect ad impressions and revenue.

Result (from the sample printout)

  • Android (Free): 8,864 rows × 13 columns
  • iOS (Free): 4,056 rows × 16 columns

Caveats

  • Price values are strings; strict string comparisons are used ('0'/'0.0').
    If you later cast to float, use float(price) == 0.0 for robustness.
  • Column positions are dataset-specific and assumed known (-6 for Android price, 4 for iOS price). If schemas change, update indices accordingly.
In [19]:
# Isolating Free Android Apps
free_android_apps = []

for app in android_english:
    price = app[-6]
    
    if price == '0' or price == '0.0':
        free_android_apps.append(app)
        
# Isolating Free iOS Apps
free_ios_apps = []

for app in ios_english:
    price = app[4]
    
    if price == '0' or price == '0.0':
        free_ios_apps.append(app)
        
# Explore the filtered datasets
print("Android Free Apps:")
explore_data(free_android_apps, 0, 3, True)
print("\nIos Free Apps:")
explore_data(free_ios_apps, 0, 3, True)

Android Free Apps:
['Photo Editor & Candy Camera & Grid & ScrapBook', 'ART_AND_DESIGN', '4.1', '159', '19M', '10,000+', 'Free', '0', 'Everyone', 'Art & Design', 'January 7, 2018', '1.0.0', '4.0.3 and up']


['U Launcher Lite – FREE Live Cool Themes, Hide Apps', 'ART_AND_DESIGN', '4.7', '87510', '8.7M', '5,000,000+', 'Free', '0', 'Everyone', 'Art & Design', 'August 1, 2018', '1.2.4', '4.0.3 and up']


['Sketch - Draw & Paint', 'ART_AND_DESIGN', '4.5', '215644', '25M', '50,000,000+', 'Free', '0', 'Teen', 'Art & Design', 'June 8, 2018', 'Varies with device', '4.2 and up']


Number of rows: 8864
Number of columns: 13

Ios Free Apps:
['284882215', 'Facebook', '389879808', 'USD', '0.0', '2974676', '212', '3.5', '3.5', '95.0', '4+', 'Social Networking', '37', '1', '29', '1']


['389801252', 'Instagram', '113954816', 'USD', '0.0', '2161558', '1289', '4.5', '4.0', '10.23', '12+', 'Photo & Video', '37', '0', '29', '1']


['529479190', 'Clash of Clans', '116476928', 'USD', '0.0', '2130805', '579', '4.5', '4.5', '9.24.12', '9+', 'Games', '38', '5', '18', '1']


Number of rows: 4056
Number of columns: 16

Validating Our App Ideas with a Lean, Data-Driven Strategy¶

Before committing major resources to full development, we take a strategic, low-risk approach to validating new app ideas. Our goal is to ensure that every project we pursue has real market traction — not just potential.

Here’s how our validation process works:

  1. Start small: We first build a minimal Android version of the app and release it on Google Play.
  2. Measure early success: If user feedback, ratings, and engagement metrics look promising, we continue refining the Android app.
  3. Scale what works: After six months, if the app shows sustained growth and profitability, we expand by building an iOS version and releasing it on the App Store.

Because our long-term objective is to publish successful apps on both platforms, we need to understand which types of apps thrive across both ecosystems. For example, a productivity app that incorporates gamification might perform well on Android and iOS alike.

To uncover these cross-market success patterns, we’ll begin our analysis by exploring the most common genres in each marketplace — starting with frequency tables to identify where the biggest opportunities lie.

In [20]:
# Most common apps by genre
# Create a frequency table function


def freq_table(dataset, index):
    app_dictionary = {}
    total = len(dataset)
    
    for app in dataset:
        app_index = app[index]
        
        if app_index in app_dictionary:
            app_dictionary[app_index] += 1
        else:
            app_dictionary[app_index] = 1
            
    table_percentages = {key: (value / total) * 100 for key, value in app_dictionary.items()}
    
    return table_percentages

android_header = ['App', 'Category', 'Rating', 'Reviews', 'Size', 'Installs', 'Type', 'Price', 'Content Rating', 'Genres', 'Last Updated', 'Current Ver', 'Android Ver']
ios_header = ['id', 'track_name', 'size_bytes', 'currency', 'price', 'rating_count_tot', 'rating_count_ver', 'user_rating', 'user_rating_ver', 'ver', 'cont_rating', 'prime_genre', 'sup_devices.num', 'ipadSc_urls.num', 'lang.num', 'vpp_lic']

def display_table(dataset, index):
    table = freq_table(dataset, index)
    table_display = []
    for key in table:
        key_val_as_tuple = (table[key], key)
        table_display.append(key_val_as_tuple)
        
    table_sorted = sorted(table_display, reverse=True)
    for entry in table_sorted:
        print(f"{entry[1]} : {entry[0]}")

print('Android Genre Frequency Table:')
display_table(free_android_apps, 9)
print("\nAndroid Category Frequency Table:")
display_table(free_android_apps, 1)
print("\niOS Prime Genre Frequency Table:")
display_table(free_ios_apps, -5)

        

Android Genre Frequency Table:
Tools : 8.449909747292418
Entertainment : 6.069494584837545
Education : 5.347472924187725
Business : 4.591606498194946
Productivity : 3.892148014440433
Lifestyle : 3.892148014440433
Finance : 3.7003610108303246
Medical : 3.531137184115524
Sports : 3.463447653429603
Personalization : 3.3167870036101084
Communication : 3.2378158844765346
Action : 3.1024368231046933
Health & Fitness : 3.0798736462093865
Photography : 2.944494584837545
News & Magazines : 2.7978339350180503
Social : 2.6624548736462095
Travel & Local : 2.3240072202166067
Shopping : 2.2450361010830324
Books & Reference : 2.1435018050541514
Simulation : 2.0419675090252705
Dating : 1.861462093862816
Arcade : 1.8501805054151623
Video Players & Editors : 1.7712093862815883
Casual : 1.7599277978339352
Maps & Navigation : 1.3989169675090252
Food & Drink : 1.2409747292418771
Puzzle : 1.128158844765343
Racing : 0.9927797833935018
Role Playing : 0.9363718411552346
Libraries & Demo : 0.9363718411552346
Auto & Vehicles : 0.9250902527075812
Strategy : 0.9138086642599278
House & Home : 0.8235559566787004
Weather : 0.8009927797833934
Events : 0.7107400722021661
Adventure : 0.6768953068592057
Comics : 0.6092057761732852
Beauty : 0.5979241877256317
Art & Design : 0.5979241877256317
Parenting : 0.4963898916967509
Card : 0.45126353790613716
Casino : 0.42870036101083037
Trivia : 0.41741877256317694
Educational;Education : 0.39485559566787
Board : 0.3835740072202166
Educational : 0.3722924187725632
Education;Education : 0.33844765342960287
Word : 0.2594765342960289
Casual;Pretend Play : 0.236913357400722
Music : 0.2030685920577617
Racing;Action & Adventure : 0.16922382671480143
Puzzle;Brain Games : 0.16922382671480143
Entertainment;Music & Video : 0.16922382671480143
Casual;Brain Games : 0.13537906137184114
Casual;Action & Adventure : 0.13537906137184114
Arcade;Action & Adventure : 0.12409747292418773
Action;Action & Adventure : 0.10153429602888085
Educational;Pretend Play : 0.09025270758122744
Simulation;Action & Adventure : 0.078971119133574
Parenting;Education : 0.078971119133574
Entertainment;Brain Games : 0.078971119133574
Board;Brain Games : 0.078971119133574
Parenting;Music & Video : 0.06768953068592057
Educational;Brain Games : 0.06768953068592057
Casual;Creativity : 0.06768953068592057
Art & Design;Creativity : 0.06768953068592057
Education;Pretend Play : 0.056407942238267145
Role Playing;Pretend Play : 0.04512635379061372
Education;Creativity : 0.04512635379061372
Role Playing;Action & Adventure : 0.033844765342960284
Puzzle;Action & Adventure : 0.033844765342960284
Entertainment;Creativity : 0.033844765342960284
Entertainment;Action & Adventure : 0.033844765342960284
Educational;Creativity : 0.033844765342960284
Educational;Action & Adventure : 0.033844765342960284
Education;Music & Video : 0.033844765342960284
Education;Brain Games : 0.033844765342960284
Education;Action & Adventure : 0.033844765342960284
Adventure;Action & Adventure : 0.033844765342960284
Video Players & Editors;Music & Video : 0.02256317689530686
Sports;Action & Adventure : 0.02256317689530686
Simulation;Pretend Play : 0.02256317689530686
Puzzle;Creativity : 0.02256317689530686
Music;Music & Video : 0.02256317689530686
Entertainment;Pretend Play : 0.02256317689530686
Casual;Education : 0.02256317689530686
Board;Action & Adventure : 0.02256317689530686
Video Players & Editors;Creativity : 0.01128158844765343
Trivia;Education : 0.01128158844765343
Travel & Local;Action & Adventure : 0.01128158844765343
Tools;Education : 0.01128158844765343
Strategy;Education : 0.01128158844765343
Strategy;Creativity : 0.01128158844765343
Strategy;Action & Adventure : 0.01128158844765343
Simulation;Education : 0.01128158844765343
Role Playing;Brain Games : 0.01128158844765343
Racing;Pretend Play : 0.01128158844765343
Puzzle;Education : 0.01128158844765343
Parenting;Brain Games : 0.01128158844765343
Music & Audio;Music & Video : 0.01128158844765343
Lifestyle;Pretend Play : 0.01128158844765343
Lifestyle;Education : 0.01128158844765343
Health & Fitness;Education : 0.01128158844765343
Health & Fitness;Action & Adventure : 0.01128158844765343
Entertainment;Education : 0.01128158844765343
Communication;Creativity : 0.01128158844765343
Comics;Creativity : 0.01128158844765343
Casual;Music & Video : 0.01128158844765343
Card;Action & Adventure : 0.01128158844765343
Books & Reference;Education : 0.01128158844765343
Art & Design;Pretend Play : 0.01128158844765343
Art & Design;Action & Adventure : 0.01128158844765343
Arcade;Pretend Play : 0.01128158844765343
Adventure;Education : 0.01128158844765343

Android Category Frequency Table:
FAMILY : 18.907942238267147
GAME : 9.724729241877256
TOOLS : 8.461191335740072
BUSINESS : 4.591606498194946
LIFESTYLE : 3.9034296028880866
PRODUCTIVITY : 3.892148014440433
FINANCE : 3.7003610108303246
MEDICAL : 3.531137184115524
SPORTS : 3.395758122743682
PERSONALIZATION : 3.3167870036101084
COMMUNICATION : 3.2378158844765346
HEALTH_AND_FITNESS : 3.0798736462093865
PHOTOGRAPHY : 2.944494584837545
NEWS_AND_MAGAZINES : 2.7978339350180503
SOCIAL : 2.6624548736462095
TRAVEL_AND_LOCAL : 2.33528880866426
SHOPPING : 2.2450361010830324
BOOKS_AND_REFERENCE : 2.1435018050541514
DATING : 1.861462093862816
VIDEO_PLAYERS : 1.7937725631768955
MAPS_AND_NAVIGATION : 1.3989169675090252
FOOD_AND_DRINK : 1.2409747292418771
EDUCATION : 1.1620036101083033
ENTERTAINMENT : 0.9589350180505415
LIBRARIES_AND_DEMO : 0.9363718411552346
AUTO_AND_VEHICLES : 0.9250902527075812
HOUSE_AND_HOME : 0.8235559566787004
WEATHER : 0.8009927797833934
EVENTS : 0.7107400722021661
PARENTING : 0.6543321299638989
ART_AND_DESIGN : 0.6430505415162455
COMICS : 0.6204873646209386
BEAUTY : 0.5979241877256317

iOS Prime Genre Frequency Table:
Games : 55.64595660749507
Entertainment : 8.234714003944774
Photo & Video : 4.117357001972387
Social Networking : 3.5256410256410255
Education : 3.2544378698224854
Shopping : 2.983234714003945
Utilities : 2.687376725838264
Lifestyle : 2.3175542406311638
Finance : 2.0710059171597637
Sports : 1.947731755424063
Health & Fitness : 1.8737672583826428
Music : 1.6518737672583828
Book : 1.6272189349112427
Productivity : 1.5285996055226825
News : 1.4299802761341223
Travel : 1.3806706114398422
Food & Drink : 1.0601577909270217
Weather : 0.7642998027613412
Reference : 0.4930966469428008
Navigation : 0.4930966469428008
Business : 0.4930966469428008
Catalogs : 0.22189349112426035
Medical : 0.19723865877712032

Market Pulse: What the Frequency Tables Say¶

Apple App Store — Prime Genre (iOS)¶

  • Most common: Games (55.65%)
  • Next most common: Entertainment (8.23%)
  • Other notable shares: Photo & Video (4.12%), Social Networking (3.53%), Education (3.25%), Shopping (2.98%), Utilities (2.69%)

Patterns & impression

  • The iOS landscape is heavily entertainment-skewed. Over half of the catalog is Games, followed by other attention-economy genres (Entertainment, Photo & Video, Social).
  • Practical categories (Utilities, Productivity, Finance, Education) are a smaller slice of the store relative to entertainment.

Can we recommend a profile from frequency alone?

  • Caution: High supply ≠ high users. A large number of Games apps indicates saturation, not necessarily opportunity.
  • From frequency alone, a safer lane is a practical app with entertainment DNA (e.g., Productivity/Education enriched with light gamification). It positions us away from the heaviest competition while tapping proven engagement mechanics.

Google Play — Category & Genres (Android)¶

  • Top Categories: FAMILY (18.91%), GAME (9.72%), TOOLS (8.46%), BUSINESS (4.59%), LIFESTYLE (3.90%), PRODUCTIVITY (3.89%)
  • Top Genres: Tools (8.45%), Entertainment (6.07%), Education (5.35%), Business (4.59%), Productivity (3.89%), Lifestyle (3.89%)

Patterns & impression

  • Android shows a stronger utility and family footprint: FAMILY and TOOLS dominate structurally, with solid presence from BUSINESS, PRODUCTIVITY, and EDUCATION.
  • Entertainment is meaningful (GAME, Entertainment) but less dominant than on iOS.
  • Long tail of niche/compound genres (e.g., Casual;Pretend Play, Video Players & Editors;Music & Video) suggests fragmentation and lots of micro-segments.

Can we recommend a profile from frequency alone?

  • Frequency again reflects supply, not demand. We need Installs (Android) and rating/review counts as demand proxies before making a call.
  • That said, Android’s catalog composition favors practical value. Profiles in Tools/Productivity/Education look structurally aligned with the market, especially if they solve a clear, everyday problem.

Cross-Market Read: iOS vs. Android¶

  • iOS: Entertainment-heavy; Games is the gravity well.
  • Android: More utilitarian; FAMILY/TOOLS/PRODUCTIVITY loom larger.
  • Implication for a dual-platform strategy: Build a practical app with playful hooks. Think Productivity/Education with gamified progress, social nudges, and light media features. This threads the needle: credible utility for Android, engaging surface area for iOS.

Recommendation (Provisional) & Next Steps¶

Provisional profile:

  • Core: Productivity or Education
  • Layering: Gamification (streaks, badges), lightweight social, and shareable visuals to mirror iOS engagement norms without abandoning Android’s utility bias.
  • Positioning: Solve a persistent, cross-platform pain point (e.g., habit/skill tracking, micro-learning, daily planning) with low friction and delightful feedback loops.

Crucial next steps to move from “supply view” → “demand view”:

  1. Weight by demand:
    • Android: aggregate by Installs (e.g., median/mean installs per genre) and rating_count.
    • iOS: use rating_count_tot as a user proxy.
  2. Quality screen: Compare average rating and review density per genre to avoid high-install but low-satisfaction pockets.
  3. Concentration check: Identify genres where top-decile apps capture outsized demand (winner-takes-most risk) vs. healthier distributions.
  4. Profit fit: Since we’re ad-supported, prioritize genres with frequent daily usage and session depth (historically: productivity trackers, light education, utilities with recurring tasks).

Bottom line: Frequency tables are a great map of the supply side. To green-light an idea, we now need to marry this with demand signals (installs, reviews, ratings) and engagement potential to pick the best cross-market bet.

In [11]:
# Most Popular Apps by Genre in App Store

def freq_table(dataset, index):
    app_dictionary = {}
    total = len(dataset)
    
    for app in dataset:
        app_index = app[index]
        
        if app_index in app_dictionary:
            app_dictionary[app_index] += 1
        else:
            app_dictionary[app_index] = 1
            
    table_percentages = {key: (value / total) * 100 for key, value in app_dictionary.items()}
    
    return table_percentages

genres_ios = freq_table(free_ios_apps, -5)

for genre in genres_ios:
    total = 0  # To store the sum of user ratings
    len_genre = 0  # To store number of apps in each genre

    for app in free_ios_apps:
        genre_app = app[-5]
        
        if genre_app == genre:
            user_ratings = float(app[5]) 
            total += user_ratings
            len_genre += 1
            
    if len_genre > 0:  # Avoid division by zero
        avg_user_ratings = round(total / len_genre, 2)
        print(f"Genre: {genre}, Average User Ratings: {avg_user_ratings}")
        

Genre: Social Networking, Average User Ratings: 53078.2
Genre: Photo & Video, Average User Ratings: 27249.89
Genre: Games, Average User Ratings: 18924.69
Genre: Music, Average User Ratings: 56482.03
Genre: Reference, Average User Ratings: 67447.9
Genre: Health & Fitness, Average User Ratings: 19952.32
Genre: Weather, Average User Ratings: 47220.94
Genre: Utilities, Average User Ratings: 14010.1
Genre: Travel, Average User Ratings: 20216.02
Genre: Shopping, Average User Ratings: 18746.68
Genre: News, Average User Ratings: 15892.72
Genre: Navigation, Average User Ratings: 25972.05
Genre: Lifestyle, Average User Ratings: 8978.31
Genre: Entertainment, Average User Ratings: 10822.96
Genre: Food & Drink, Average User Ratings: 20179.09
Genre: Sports, Average User Ratings: 20128.97
Genre: Book, Average User Ratings: 8498.33
Genre: Finance, Average User Ratings: 13522.26
Genre: Education, Average User Ratings: 6266.33
Genre: Productivity, Average User Ratings: 19053.89
Genre: Business, Average User Ratings: 6367.8
Genre: Catalogs, Average User Ratings: 1779.56
Genre: Medical, Average User Ratings: 459.75

iOS Popularity by Genre (Based on rating_count_tot Averages)¶

What this measures
This analysis uses the average rating_count_tot for each prime_genre as a proxy for user engagement. A higher average suggests a larger user base or more frequent user interaction.

Most Popular Genres (Highest Average Total Ratings)

  1. Reference — 67,448
  2. Music — 56,482
  3. Social Networking — 53,078
  4. Weather — 47,221
  5. Photo & Video — 27,250
  6. Navigation — 25,972
  7. Travel — 20,216
  8. Food & Drink — 20,179
  9. Sports — 20,129
  10. Health & Fitness — 19,952
  11. Productivity — 19,054

Least Popular Genres (Lowest Average Total Ratings)

  • Catalogs — 1,780
  • Medical — 460

Observations

  • Genres such as Reference, Music, and Social Networking have the highest average total ratings, indicating broad appeal and large, engaged audiences.
  • Weather and Navigation also rank high, suggesting consistent daily use cases rather than purely entertainment-driven engagement.
  • Productivity, Health & Fitness, and Travel fall into a middle range — moderately popular and likely to attract stable, recurring users.
  • Lower averages in Education, Business, and Medical imply more niche or specialized audiences.

General Impression The App Store market is divided between utility-driven apps (Reference, Weather, Navigation, Productivity) and entertainment or lifestyle apps (Music, Social Networking, Photo & Video). The data shows that apps offering practical or habitual use—such as checking weather or looking up information—tend to accumulate higher user counts over time.

App Profile Recommendation Based on the data alone, a Reference or Weather-based app would be the most logical starting point for user reach.

  • Reference apps are widely used and maintain steady engagement without requiring constant new content.
  • Weather apps show habitual, daily use patterns, which align well with an ad-supported business model.

A practical, information-focused app that encourages frequent, short user sessions would likely perform well given these trends.

In [12]:
# Most Popular Apps by Genre in Google Play Store

categories_android = freq_table(free_android_apps, 1)

for category in categories_android:
    total = 0  # To store the sum of installs
    len_category = 0  # To store number of apps in each category

    for app in free_android_apps:
        category_app = app[1]
        
        if category_app == category:
            num_installs = app[5].replace('+', '').replace(',', '')
            num_installs = float(num_installs)
            total += num_installs
            len_category += 1
            
    if len_category > 0:  # Avoid division by zero
        avg_installs = round(total / len_category, 2)
        print(f"Category: {category}, Average Installs: {avg_installs}")

Category: ART_AND_DESIGN, Average Installs: 1986335.09
Category: AUTO_AND_VEHICLES, Average Installs: 647317.82
Category: BEAUTY, Average Installs: 513151.89
Category: BOOKS_AND_REFERENCE, Average Installs: 8767811.89
Category: BUSINESS, Average Installs: 1712290.15
Category: COMICS, Average Installs: 817657.27
Category: COMMUNICATION, Average Installs: 38456119.17
Category: DATING, Average Installs: 854028.83
Category: EDUCATION, Average Installs: 1833495.15
Category: ENTERTAINMENT, Average Installs: 11640705.88
Category: EVENTS, Average Installs: 253542.22
Category: FINANCE, Average Installs: 1387692.48
Category: FOOD_AND_DRINK, Average Installs: 1924897.74
Category: HEALTH_AND_FITNESS, Average Installs: 4188821.99
Category: HOUSE_AND_HOME, Average Installs: 1331540.56
Category: LIBRARIES_AND_DEMO, Average Installs: 638503.73
Category: LIFESTYLE, Average Installs: 1437816.27
Category: GAME, Average Installs: 15588015.6
Category: FAMILY, Average Installs: 3695641.82
Category: MEDICAL, Average Installs: 120550.62
Category: SOCIAL, Average Installs: 23253652.13
Category: SHOPPING, Average Installs: 7036877.31
Category: PHOTOGRAPHY, Average Installs: 17840110.4
Category: SPORTS, Average Installs: 3638640.14
Category: TRAVEL_AND_LOCAL, Average Installs: 13984077.71
Category: TOOLS, Average Installs: 10801391.3
Category: PERSONALIZATION, Average Installs: 5201482.61
Category: PRODUCTIVITY, Average Installs: 16787331.34
Category: PARENTING, Average Installs: 542603.62
Category: WEATHER, Average Installs: 5074486.2
Category: VIDEO_PLAYERS, Average Installs: 24727872.45
Category: NEWS_AND_MAGAZINES, Average Installs: 9549178.47
Category: MAPS_AND_NAVIGATION, Average Installs: 4056941.77

Google Play Popularity by Category (Based on Average Installs)¶

What this measures
Each value represents the average number of installs for free apps within a category on Google Play. Higher averages suggest categories with broader reach or higher user activity, though results can be skewed by a few large apps.

Categories with the highest average installs

  • Communication — 38.46M
  • Video Players — 24.73M
  • Social — 23.25M
  • Productivity — 16.79M
  • Photography — 17.84M
  • Game — 15.59M
  • Travel & Local — 13.98M
  • Tools — 10.80M
  • Entertainment — 11.64M
  • News & Magazines — 9.55M
  • Books & Reference — 8.77M
  • Shopping — 7.04M

Categories with lower average installs

  • Medical — 0.12M
  • Events — 0.25M
  • Parenting — 0.54M
  • Beauty — 0.51M
    These categories tend to target smaller, specialized audiences.

Observations

  • Communication, Social, and Video categories dominate by total installs, likely due to a small number of apps with extremely large user bases.
  • Utility-based categories like Productivity, Tools, and Books & Reference also show consistent engagement across a wide range of apps.
  • Travel & Local and Weather apps see steady usage, which aligns with habitual, information-driven behavior rather than entertainment.
  • Niche or specialized areas, such as Medical or Events, have comparatively limited reach.

Cross-Market Comparison

  • On the App Store, Reference apps had the highest average total ratings, while Weather and Productivity also performed well.
  • On Google Play, Books & Reference and Productivity follow similar patterns, both showing strong user numbers and practical use cases.

App Profile Recommendation A Reference or Productivity-focused app is a reasonable direction for both platforms.

  • These categories show consistent user activity on Google Play and strong engagement on iOS.
  • They are also less dependent on social or entertainment trends, making them easier to maintain over time.

A simple, information-driven app that supports recurring daily or task-based use would likely perform well across both markets.