## ── Attaching core tidyverse packages ──────────────────────── tidyverse 2.0.0 ──
## ✔ dplyr     1.1.4     ✔ readr     2.1.5
## ✔ forcats   1.0.0     ✔ stringr   1.5.1
## ✔ ggplot2   3.5.1     ✔ tibble    3.2.1
## ✔ lubridate 1.9.4     ✔ tidyr     1.3.1
## ✔ purrr     1.0.2     
## ── Conflicts ────────────────────────────────────────── tidyverse_conflicts() ──
## ✖ dplyr::filter() masks stats::filter()
## ✖ dplyr::lag()    masks stats::lag()
## ℹ Use the conflicted package (<http://conflicted.r-lib.org/>) to force all conflicts to become errors

Introduction

Today, technology is no longer all about achieving more revenues—it’s a living part of urban life. In this report, we look at urban ZIP codes in which we can observe sales of tech products along with marketing characteristics of the cities and neighborhoods and find the patterns in popularity when products were purchased, and how community traits are associated with technology buying behaviors.

The Audience

Urban policymakers and community development analysts who are interested in understanding the uses of digital lifelines linking demographics to technology use may be our intended audience.

Key Questions Addressed:

  1. Which tech product categories dominate urban tech sales, and what insights do they provide about local consumer preferences?
  2. How do seasonal and monthly trends affect tech product purchases in these urban areas?
  3. Are there notable geographic differences in tech spending across the select urban ZIP codes?
  4. How does the local demographic context (e.g., median household income, population) relate to technology spending per capita?
  5. What are the peak hours for tech product purchases, and what might this imply about urban consumer behavior?

1. Product Category Sales Distribution visualization

The bar chart below gives the total revenue per product category. It ranks the popularity of tech items in the urban micro-markets.

From the bar chart, the Other category generates the highest total revenue, followed by Mobile, Display, Audio, and finally Accessories. This implies:

  1. Other Dominates: Since Other outperforms all other defined categories, it suggests that there are either many diverse products grouped under Other, or those products command high price points (or both). This shadowing might be evidence for broader consumers interest in varied speciality items that didn’t quite fit into the named categories.

  2. Strong Showing for Mobile:The second‐highest revenue category is Mobile,reflecting that smartphones (or phone‐related products) are both in high demand and often come with relatively higher price tags. This corresponds to the notion that phones are essential to today’s digital lives.

  3. Middle Tiers (Display, Audio): Display and Audio products are in the middle range, suggesting moderate demand for monitors, TVs, and headphones. The cheaper price points might result in a more moderate total revenue, or the degree of upgrades could be less frequent than with phones.

  4. Lower Revenue for Accessories: Accessories ranks last, which often happens because items like cables or small add‐ons are lower‐cost and purchased intermittently. These are typical items to purchase, but the lower price and potentially lower quantity produce a pretty low total revenue.

The chart indicates that broad consumer preferences lean toward either a diverse set of products lumped into Other or the essential but higher‐value mobile devices. Such analysis can tell urban policy makers or urban analysts that mobile connectivity, along with a number of specialized tech products (especially those in the first prize range), may be the main drivers of tech engagement for these ZIP codes.

2: Monthly Revenue Trend Visualization

Line graph that shows how technology purchases evolve over the year. A monthly revenue trend can reveal seasonal patterns or specific months where tech adoption spikes.

The line chart shows how total revenue from tech products fluctuates month by month, revealing clear “peaks” and “valleys” over the course of 2019:

Timing from policy or community initiative perspective is critical. Urban policy makers know such a thing as when people are most ready to buy tech products (early spring, late fall) and can schedule community tech fairs, digital literacy programs, or device subsidy initiatives at these times of the greatest interest in tech. On the other hand, they may focus on outreach when there are more people purchasing to make tech adoption equitable throughout the year.

3. City-Level Sales Analysis Visualization

This bar chart shows a comparison of total revenue across cities (each represented by a single urban ZIP code) against shed light on geographic differences in tech engagement.

This bar chart plots the difference in total tech product revenue between each individual ZIP code in a city or cities.The implications are:

  1. San Francisco Leads: The highest bar belongs to San Francisco, which may reflect a combination of factors such as higher average income, a strong tech culture, or a greater propensity to invest in new devices. Although we are only talking about one ZIP code, it is possible that this particular area is particularly wealthy or techy.

  2. Los Angeles and New York City Follow: Los Angeles and New York City, both large urban centers, also show strong spending, though not at San Francisco’s level. They have diverse populations and are economically active enough to make a lot of mobile device, monitor, and other electronics purchases.

  3. Middle Tier (Boston, Atlanta, Dallas, Seattle): These cities’ ZIP codes occupy the middle of the chart. This may be their revenue level which could denote moderate household incomes, cultural preferences or a more balanced tech spending by consumers. Demographics and local economies of each city can affect the demand technology products.

  4. Lower Revenue (Portland, Austin):The bars for Portland and Austin are the smallest, which could indicate lower overall spending in the ZIP codes included. Perhaps, it is related to demographic factors (like having a lower population in that particular ZIP) or cultural differences in how people buy tech.

The variation across cities suggests that the same product on different markets differingly resonates depending on local demographics, income levels, cultural preferences, or population. It might be useful to generalize an entire city based on the data available (one per ZIP Code), but these findings are really showing what happened on these particular neighborhoods, not the city. However, the patterns indicate that some urban ZIP codes are more tech active than others and it is worth further investigation into what drives higher spending in some urban ZIP codes than others.

4. Linking Demographics with Revenue per Capita Visualization

The sales data with demographic info to compute revenue per capita by ZIP code is merged and plotted in a scatter plot. Plotting this against median household income, exploration on how wealthier communities tend to spend more on technology per person can be investigated.

## `geom_smooth()` using formula = 'y ~ x'

This scatter plot shows a scaling of median household income with technology spending per capita with most points on the left (low median household income) and some points (mostly indicative of housing areas) in the right tail (high median household income:

While the sample is limited to one ZIP code per city, the plot shows a connection between local wealth and tech spending intensity, highlighting how demographic and economic factors can shape the adoption of technology

5. Hourly Distribution of Tech Purchases Visualization

An histogram is used to analyse the time-of-day patterns in tech purchases. It shows when urban consumers are most active in their tech shopping.

Tech purchases as shown in the histogram are evenly dispersed during the day, except with significant amounts in late morning to early afternoon and then again in the early evening.

  1. Slow Early Hours (Midnight–6 AM): Transaction counts are relatively low overnight, which aligns with typical sleep schedules. At this point most consumers are unlikely to shop online, leaving one with basically no sales.

  2. Midmorning to Midday Surge (9 AM–2 PM): There is a clear jump in purchases starting around midmorning, peaking around lunchtime. The pattern could mean that people are shopping while they are on their breaks at work or on their personal devices while looking at deals in midday slumps.

  3. Evening Activity (5 PM–9 PM): Another elevated period of transactions occurs in the evening. It is possible that consumers are buying at the end of the day or after a period of leisure time, aided by their day’s routine (e.g. checking social media, and visiting online stores)

  4. Policy and Community Implications:

    • Targeted Outreach: Urban policy makers or community organizers could schedule digital literacy workshops or device‐upgrade campaigns around these peak hours to maximize visibility and engagement.

    • Promotional Timing: Businesses or non‐profit tech initiatives may see better response rates if they align promotions with these busier shopping windows.

The hourly breakdown provides insights into when urban consumers are most likely to shop online, highlighting midday and evening as prime windows for engagement and outreach.

Conclusion

In conclusion ,the various visualizations together paint a multifaceted picture of how particular urban ZIP codes purchased technology. The first visualization shows that ‘Other’ types of product bring in more revenue than most, suggesting that there are a wide as yet unclassified types of items that can have a high market share. At the same time, the monthly revenue trend draws attention to the seasonality as expressed in occasional peaks in the early spring and the end of the year which may be linked to the holidays, promotions, or the changing consumer behaviour. At the city level, the revenue is extremely varied with San Francisco recording the highest revenue, which is likely because of its high local incomes or a stronger tech culture, and other cities ranking in at varying levels. This relationship between median household income and revenue per capita just further solidifies the fact that the more economic factors drive spending, the more they drive consumer spending, so the spending is higher in higher income ZIP codes, which suggests that there is a potential digital divide. For lastly, the hourly distribution shows that consumers shop most of the time from midmorning to early afternoon and also in the late morning, indicating the working and private time. Together these insights tell policymakers and business how demographics, timing, and preferences around product converge to determine the tech purchasing geography of these urban neighborhoods. Also, the highlight ways of further research.