Why is social media the ultimate source of consumer data?
Well, to put it simply. Considering the amount of time the average consumer spends on not one but multiple platforms daily is enough of an answer.
Since we believe in the importance of data, let’s take a look at some numbers:
- Over 75% of the world’s population aged 13+ uses social media.
- Worldwide, people spend an average of 2 hours and 28 minutes per day.
- 62.3% of Instagram users worldwide say they use the platform to follow or research brands and products.
Social media is now an extension of our lives. As of 2024, there are 4.8 billion people in the world who use social media – over half the global population.
Users willingly share a vast amount of personal information on these platforms.
They share their opinions, preferences, and activities through posts, comments, likes, and shares.
This voluntary sharing provides a rich dataset for understanding consumer behaviour and preferences.
How does Heuritech leverage social media?
At Heuritech, we forecast market demand through consumer data.
This is done by applying product-focused computer vision on big data panels representative of each geo-market to quantify what people wear worldwide, and like that, we can anticipate market shifts.
This article explains the process of how Heuritech’s AI solution works.
It starts with defining consumer segments on social media.
The first step in Heuritech’s predict demand process is defining consumer panels, or segments, from social media. We have three major consumer panels: edgy, trendy, and mainstream.
1. Edgy: These consumers adopt a look or product far before it arrives on the popular radar, and they seek styles from small or emerging brands.
2. Trendy: These consumers keep up with new and desirable brands, styles, and products and tend to wear trends when they’re at the peak of their popularity.
3. Mainstream: These consumers follow along with major styles and products once they’ve reached peak popularity and engage more passively in fashion.
Our panels are divided into geographies, including accounts from Europe, France, the United Kingdom, the US, the Middle East, China, South Korea, Japan, Brazil, Taiwan, Thailand, Singapore, Malaysia, Philippines and Indonesia.
Each geo-specific panel contains more than 50K Instagram accounts and 400K Weibo accounts from China, which are then segmented into the consumer panels mentioned above.
Image: Nike
These panels are regularly updated and cleaned to avoid the risk of incorporating data from inactive or irrelevant accounts.
Applying our image recognition technology.
Once we’ve defined and refined our consumer panels, we then move on to analysing the images themselves in order to pull out styles and products.
Heuritech does this by using our in-house computer vision (or image recognition) technology, which was created by our two co-founders with PhDs in Artificial Intelligence. To ensure consistent precision, our data experts constantly improve and innovate upon this technology.
Our technology analyses every detail of an image, including colour, shape, and texture, to extract over 2000 details.
This data is then cross-referenced with consumer segments, geography, and seasonality for a more accurate and specific analysis.
Image: Data from Heuritech’s Market Insights platform
For example, we recently identified Tube Tops as a key style for Spring 2023 in the UK, using a combination of expert analysis and AI-powered data analysis.
For niche and emerging styles, this combination is how Heuritech is able to be so accurate in its market dynamics analyses.
Our database of about 120 million posts continues to grow, providing our team of experts and users of our platform with endless data to be transformed into actionable insights.
Predicting market demand up to one year in advance.
Now, in order to transform our data into proper insights, Heuritech applies what we like to call our forecasting toolkit — this toolkit is essentially one master algorithm that is a combination of 7 different predicting algorithms.
This machine learning algorithm allows us to predict how styles and products will behave up to one year in advance with 90% accuracy.
Digesting this data into actionable insights.
The final step in our predictive analysis is, of course, to digest it into actionable data.
Fashion and sportswear brands must be able to read and understand the data we extract from Instagram, Weibo, and other platforms in order to apply this information to their own collections and communication.
Thus, all our data is digested and divided into diverse metrics so users of our platform can guide themselves and leverage the data insights according to their own strategies.
Examples of our metrics include:
- Consumer segmentation: Edgy, trendy, and mainstream consumer panels help brands understand and make decisions based on existing or aspirational audiences.
- Geography: Style and product data are specific to each geographical region (Europe, France, the United Kingdom, the US, the Middle East, China, South Korea, Japan, Brazil, Taiwan, Thailand, Singapore, Malaysia, Philippines and Indonesia) for global brands’ adaptability to their various markets.
- Seasonality: Insights like optimal launch times and high seasons allow brands to avoid missing big trends and avoid including declining ones.
- Growth: A trend or product’s visibility on social media compared to the same season the year prior gives brands a legible view of a trend’s popularity or decline.
- Magnitude: A trend or product’s potential market demand during the season of interest helps brands judge a trend’s future demand.
Our platform also counts with different sections that target and cater to diverse purposes within teams.
For instance, merchandisers generally use “Assortment Mix” for better demand planning, and designers use the “Themes” category to gather inspiration for future collections.
However, members of all teams leverage all sections of our platform to gather insights that help them be more reactive to market changes.
The power of AI and human expertise.
Heuritech is a testament to the power of leveraging data analytics to cater to your consumers.
Our combination of qualitative and quantitative data in all sections of our platform provides a complete 360° view of how to cater to consumers successfully.
Our approach relies on data. However, by combining it with our fashion experts’ knowledge, we are able to conduct a comprehensive level of analysis that encompasses both qualitative and quantitative insights.
Our solution helps fashion and sportswear brands to produce only what their consumers want and reduce the number of unsold products—leading to increased sell-through, better profitability and greater brand relevance.
Image: Data from Heuritech’s Market Insights platform
Intuition is not replaced; it’s just confirmed.
Data-driven decision-making empowers teams with a clear vision of their market.
Armed with these insights, they are able to explore and discover new ways to cater to their consumers while anticipating sudden market shifts.
