Reviews and bold claims sell best in Luggage & Bags on TikTok Shop

1. Introduction

Brands and creators in Luggage & Bags must decide what to sell, at what price and commission, and what kind of video to make. Prior work on short-video popularity shows that early popularity predicts later popularity and that attention is long-tailed [1]. State-of-the-art prediction systems find that creator features matter most, with content features adding smaller gains [2, 3]. Less is known about which content choices are associated with sales rather than views. This paper asks what sells in one category: how the market is moving, where sales happen, which products and prices carry revenue, and which hooks, formats and production styles are associated with more sales per view.

2. Data

The window runs from 2 September to 1 October 2026. We tracked 592 videos in Luggage & Bags, and our AI analyst watched and analysed 105 of them in depth. Market comparisons use 3,342 watched videos across all categories. Marketplace figures rest on 100 top-selling products in this category, which is one of 28 categories ranked by revenue. For each video we recorded its hook, format and production style, along with whether it was boosted with ads. For products we recorded price, affiliate commission rate, launch date and sales channel. Market-level momentum and channel figures are as of 29 September 2026 and price figures as of 1 October 2026. The hook, format and production groups include only videos classified in each dimension, so their counts are smaller than 105.

Daily rankings of top-selling TikTok Shop videos in the US were collected from several independent sources and merged into one record per video. Where sources overlap, their sales estimates are cross-checked against each other, and videos whose estimates disagree by more than half are flagged. An AI analyst watched each video and recorded its opening, format, angle, production style, use of AI, hook source, length, pacing and what appears in the first second, without seeing how the video sold. Sales per view is a video group’s revenue per view divided by the market’s, shrunk toward the average for small groups, with 90% ranges. Weekly category figures for the US (estimated revenue, its split between video, LIVE and the shop tab, affiliate revenue, shops and active products, and a year of weekly revenue) and daily rankings of each category’s top-selling products (unit price, commission rate, launch date and revenue by channel) were collected from several independent sources. Medians of price and commission are weighted by revenue; momentum compares the latest weeks with the same number of weeks before. This paper covers 2026-09-02 to 2026-10-01: 592 videos tracked in Luggage & Bags, 105 of them watched and analysed; the market baseline uses all 3,342 watched videos; 100 top-selling products in Luggage & Bags. Predictions come from a logistic model retrained daily and tested on recent weeks it had not seen.

3. Methods

Sales per view is a group of videos' revenue per view divided by the market's, so 1 is the market average. Small groups are shrunk toward the average by empirical Bayes [4], and we report 90% intervals on the log scale. The predictive model is a logistic model of top-selling videos, retrained daily and tested on recent weeks it had not seen. We report AUC [5] with a bootstrap range [6]. Momentum compares estimated revenue in the latest 4 and 13 weeks with the same number of weeks before. Channel shares split the latest week's revenue into shoppable video, LIVE and the shop tab, plus the share credited to affiliate creators. Prices, commission and product age are computed for the top-selling products, with medians weighted by revenue and revenue per product set against the average product. Competition uses shops, active products, average revenue per shop, the top ten products' share and the Herfindahl–Hirschman index [7]. Seasonality compares each month with an average month over the past year, leaving out partial months, in the spirit of seasonal-trend separation [8].

4. Results: momentum, channels and competition

Luggage & Bags accounted for 1.5% of market revenue over the latest four weeks and ranked 21st of 28 categories. Revenue in the latest four weeks was 13.8% above the previous four. Over 13 weeks it is 12% below the preceding 13, against a market-wide fall of 11.1%, so the longer decline is close to the market's. In the latest week 61.3% of category revenue came through shoppable video, 21.4% through LIVE and 17.3% through the shop tab, compared with 64.9%, 17.1% and 18% for the market. Affiliate creators were credited with 72.9% of category revenue. Competition is moderate: 3,854 shops and 21,385 active products, with average revenue per shop of $1,708 against $2,401 in the median category. The top ten tracked products hold 29.7% of top-product revenue, the same as the median category, and the Herfindahl–Hirschman index is 174, which indicates low concentration.

5. Results: prices, commission and product age

The revenue-weighted median price among the 100 top products is $45, and the middle half sit between $24 and $78. Revenue is spread across bands. The $20–35 band holds 28 products and 28.3% of revenue. The $60–100 band holds 23 products and 28.9% of revenue, and its revenue per product is 1.26× the average product. The $35–60 band is lower at 0.78×. The under-$10 band shows 1.31× but has only 3 products, so we do not read much into it. The revenue-weighted median commission is 9%. Products at 5–10% carry 51.5% of revenue, and those at 10–15% earn 1.09× the average product. Video accounts for 70.6% of revenue at 5–10% commission and 82.7% at 10–15%. Only 2 products pay under 5%. By age, products launched in the last 90 days make up 15.2% of top-product revenue. Products aged 3–12 months earn about 1.2× the average, while the 6 products aged 30–90 days earn 0.58×.

6. Results: formats, hooks and a predictive model

Review or testimonial videos sold at 1.8× the market in sales per view (90% range 1.4–2.4×, 18 videos, medium confidence) and took 23.8% of watched-video sales. Demo or tutorial is the most common format, with 42 videos and 42.2% of sales, but it sold at 0.7× (range 0.56–0.89×, high confidence). Unboxing reached 1.4× (range 1.1–2.0×) on 8 videos, which is low confidence. Among hooks, the bold claim reached 1.7× (range 1.3–2.2×, 14 videos, medium confidence). Price or deal reached 1.6× (range 1.2–2.2×) on only 7 videos. Relatable POV, the most common hook with 23 videos, sold at 0.8× (range 0.57–1.04×). Filmed live action covered 96.3% of sales at 1.0× (range 0.85–1.19×), so production style does not separate winners here. Our model of top-selling videos reached an AUC of 0.64 (90% range 0.57–0.70) on 2,667 training rows. It was not trained only on analyses that never saw sales (cleanOnly is false), so it is a modest signal. Its strongest associations are filmed live action (odds ratio 2.54), a visual pattern-break combined with a review or testimonial (1.92) and no visible AI (1.71).

7. Discussion

For brands, the evidence points to mid-priced products, with the $20–35 and $60–100 bands carrying most revenue, and to commission near the category median of 9%. Video-sold revenue is higher at higher commission rates. This is consistent with commission levels being set to attract affiliate promotion [9], though we cannot tell whether commission drives sales or the reverse. For creators, review, testimonial and bold-claim styles are associated with more sales per view than demos and relatable POV. That fits the idea that social proof matters in social commerce [10]. LIVE contributes 21.4% of revenue, above the market's 17.1%. Alternative explanations are many. Creator size and audience, product choice and ad boosting all differ across videos, and returns to advertising are hard to isolate from observational data [11]. Reviews may also be made for products that already sell. The long tail of active products (21,385) suggests revenue beyond the tracked top sellers [12]. We did not test price endings [13]. The seasonal view is limited to one year. Sales were 1.27× a normal month in March, and August was 0.8×, a trough before the coming moments. Halloween began on 25 September. Black Friday / Cyber Monday starts in 40 days, holiday gifting in 45 and New Year in 92. In the last year, November was 1.07× and December 1.04×, so a gifting lift is possible but modest.

8. Limitations

Most videos in the sample are top-ranked, so findings mostly separate strong sellers from good ones rather than from all videos; typical and weak videos are being added. Product figures cover the top-selling products we track in each category, not every listing, so they describe what sells best rather than everything on sale. Results are associations, not causes. Paid promotion, creator audience size and product price are not fully controlled for. Revenue, views and sales are estimates, not figures reported by TikTok. Video-level groups are small: 5 to 68 videos per group, and many are low confidence with wide ranges. The window is one month. Seasonal patterns rest on a single year. The model was not trained on sales-blind analyses (cleanOnly is false), and all findings are associations, not causal effects. Product-level figures cover 100 top-selling products, so they do not describe the category's long tail.

9. Conclusion

In Luggage & Bags, the latest month shows a short-term rebound (+13.8%) within a 13-week decline (−12%) that is close to the market's. Reviews, testimonials and bold-claim hooks are associated with higher sales per view than the more common demos and POV videos. Top-product revenue is spread across price bands and around a 9% median commission. Competition is moderate and typical of the median category. The predictive signal is modest (AUC 0.64), and the format and hook groups are small, so these findings are associations to test rather than rules.