This March, The Fintech Times is shifting its spotlight towards insurtech, such as how advanced data analysis is driving efficiencies across the insurance sector.

From enhancing risk assessment accuracy to personalising products and services, insurers are leveraging data analytics to optimise decision-making processes, mitigate risks and cater to evolving consumer needs.

Industry experts share insights into the pivotal role of data in reshaping insurance operations and strategies worldwide.

Huge impact

Data analysis, particularly predictive analytics, have made major strides to improving risk assessment in insurance, says Ashleigh Gwilliam, director of insurance industry growth at customer lifecycle intelligence platform FullCircl.

“Vast amounts of information can be analysed allowing for more accurate pricing, individualisation of policies and mitigation of future losses.

“Algorithmic analysis is also having a huge impact on actuarial departments, identifying hidden trends in data that can uncover the real reasons for claims, advanced analytics can also identify key trigger moments when a claim is likely.

“Fraudulent claims are a key concern for every insurance company. Data analytics can improve detection rates – analysing documents and information for areas of potential miss-representation and inaccuracy – whilst ensuring claims are paid quickly and cost effectively.

“In BIBA’s 2024 Manifesto, it encourages brokers to “meet the needs of the modern economy” and “respond to emerging risks”. Advanced data analytics will have an increasingly important role in modern insurance decision, identifying trends and customer needs and driving innovation in products and services.”

Streamlining workflows

Rajeev Gupta, co-founder and chief product officer of Cowbell, an adaptive cyber insurance company, suggests that advanced data analytics, particularly in cyber risk assessment, enables businesses to gain clarity, simplify processes and improve efficiency and accuracy.

“Data analytics is not new to insurance. Actuaries have been analysing data for pricing and claims reserving for decades. However, the landscape has evolved lately, with advanced data analytics now used by insurers in all other areas of the business – from risk assessment and fraud detection to improving operational efficiency and even refining product roadmap.

“At Cowbell, we are actively assessing the cyber risk posture of over 39 million businesses in the US and the UK. With our rich data pool, we enable businesses to gain clarity about their cyber risk posture in relation to their industry peers in just minutes, while also simplifying and expediting the quoting process for agents, and making the underwriting process more objective.

“By automating processes and streamlining workflows, they are able to reduce costs, improve speed, and increase accuracy across various workflows.”

Improved efficiency

AI-driven tools are enabling personalised quoting, dynamic policy management and streamlined claims processing, according to Scott Logie, chief commercial officer at independent UK consultancy.

“Data analytics, particularly tools underpinned by AI, is powering more efficient, intelligent decision-making across the insurance pipeline and customer lifecycle.

“At the beginning of customers’ journeys, analytics is making quotes generation more personalised. Historically, insurers grouped customers into broad segments based on basic profiles. Now, machine learning models enable more datapoints to be analysed, creating accurate risk profiles for designing bespoke offers. We see this technology in action on comparison sites, which are underpinned by models trained on existing quotes for age, location, house type, and car make or model.

“Analytics is also used by insurers to manage ongoing policies. AI tools review customer data and suggest edits to premiums when a customer’s situation changes. For example, moving into a higher risk area or buying a more expensive car.

“Finally, AI is making claims decisions more efficient. Often, the basics around who, why, when and what are now dealt with automatically based on machine learning models trained on past claims. With fewer manual tasks, insurance advisors and experts can dedicate more time to complex cases and tasks that bring more value to the business.”

Better policy decisions

For Sarah Carver, head of retail banking, wealth and insurance at global financial services provider Delta Capita, insurers can make better, more informed decisions, optimise their internal processes and create value for both the business and the end customers by leveraging advanced data analysis.

“We see particular value driven in three key areas:

• Risk: Insurers can use advanced data analysis to both evaluate risk and then personalise risk assessments using both historical data and predictive scenario based modelling to predict future behaviour. This can also be meshed with individual behaviour patterns allowing for an enhanced risk picture and better policy decisions.
• Customer insights and servicing: Data-driven insights can help insurers understand customer preferences, behaviours, and needs better leading to much better servicing of these customers whether on a micro level of individual servicing or on a macro level to future product development and marketing strategies. Advanced data analysis can also help identify and prevent fraud before it occurs saving cost and retaining customer trust.
• Efficiency and precision: Whether in processing claims more efficiently through analysis to determine where time should be spent, setting precise pricing by using better data to offer both competitive pricing but also less generic ‘one size fits all’ approaches.”

Getting ahead

Alex Littlejohn, executive VP at US insurance brokerage Alliant Retail P&C, says that with the insurance industry’s increasing ability to understand analytics and uses for collected data, analytics are taking on a larger role in how underwriters review, charge and provide capacity on insurance programmes, in addition to leveraging claims analytics to understand how losses impact coverages.

“Assessments conducted based on insureds’ data affects how the insurance community rates and evaluates risks.

“From an insured perspective, analytics allow them to get ahead of underwriters’ decisions, enabling decision-making on limits and deductibles for programme optimisation, both prior to shopping the insurance market and then evaluating conditions they receive back from the market.

“We’ll always move forward in terms of how data and analytics impact decision-making, both in how clients decide to buy risk and mitigate their risk, and how insurance companies decide to provide capacity and charge for the risk.”

Better price risk

Insurance companies worldwide are adopting AI to understand better how insureds drive, says Rashid Galadanci, CEO and co-founder of Driver Technologies, an AI-based mobility tech company

“Specifically leveraging video telematics-based scoring, insurance companies can now underwrite and classify the risk based on how an individual, or even a whole fleet, really drives instead of traditional factors like credit scores or motion-only telematics, which miss critical factors like tailgating and traffic sign adherence.

“Telematics with video analysis is also incredibly valuable for the claims process for users as visual ground truth cuts substantial time and costs from the claims lifecycle and, in many cases, can eliminate any need for arbitration.

“Additionally, to assess and design safer communities, we must understand our current road infrastructure by studying anonymous road safety and road risk information to develop insights into the types of improvements we need.

“By analysing real-world, location-specific road risks derived from regular and image-based road segment data (RSD) using telematics and computer vision data, insurance companies can better price risk while educating their insureds with insights into the most dangerous intersections and best roadways to keep them safe.”

Better predictions

David Bairstow, chief product officer at EagleView, a provider of aerial insights for insurance companies in the US, underscores the critical role of data and analytics in helping insurers address significant challenges such as talent retention, increasing population density in disaster-prone areas, and economic pressures.

“The insurance industry is facing significant challenges. Employees with deep experience are retiring. Attracting new talent is proving difficult. Externally, more people now reside in areas often affected by severe events, increasing pressure on insurers to more effectively underwrite those property risks.

“Further, large-scale events also present challenges in effectively servicing insureds after such events occur. And recent inflationary trends continue to damage insurer economics.

“To stay competitive, carriers will need to use data and analytics to pro-actively assess climate risk and model property portfolio exposure. Being able to better predict catastrophic impact and forecast maximum exposure value – before events even occur – will help insurers manage their underwriting and pricing strategies.

“In the aftermath of large-scale events, property intelligence and analytics can be critical tools to help insurers better service their customers. For example, leveraging timely, high-resolution aerial imagery captured at scale across affected areas can help insurers to begin processing claims much faster and, in many cases, before First Notice of Loss (FNOL) is even filed by the insureds.

“Innovative data, analytics, and technology approaches like these will help insurers better serve their customers while also helping improve the structure and financial performance of the carriers’ property insurance portfolios.”

Improving accuracy

James Harrison, global head of insurance at Dun & Bradstreet, a business intelligence and data company.

“In today’s insurance landscape, the power of data analytics cannot be overstated. Advanced data analysis techniques are revolutionising how insurers assess risk, price policies, and make strategic decisions within the industry.

“One primary way data analysis is reshaping the insurance sector is through improving the accuracy of risk assessment. By leveraging vast amounts of data from multiple sources, insurers are better positioned to conduct real-time risk analysis for individual and systemic risks, which leads to precise underwriting decisions and reduced exposure to losses in a volatile risk environment.

“Moreover, data analytics enables insurers to personalise products and services to meet the evolving needs of customers. By analysing data like customer demographics, behaviour and preferences, lifestyle habits; insurers can tailor offerings, pricing, and coverage options according to the consumers; thus enhancing customer satisfaction and loyalty.

“Data analytics is empowering the insurance industry by utilising data-driven decision-making to optimise the entire value chain. In a competitive landscape today, insurers who embrace these technologies and leverage the power of data will not only simply survive but also set a precedent for a new era of more customer centric innovation.”

Digital transformation has spawned many new businesses and remade others. Identifying and monitoring competitors has never been more critical.

ChatGPT can help identify and analyze direct and indirect competitors, including those you’ve not heard of. Here are some essential prompts.

Identify Competitors

ChatGPT’s assessment of competitors is useful for understanding a brand’s positioning in the tool’s knowledge base. New companies will need to provide ChatGPT with background info on their industry and products. For testing, however, I pretended to be the founder of Substack. Here’s my prompt:

I am the founder of Substack. Who are my competitors?

ChatGPT’s response was spot on:

1. Newsletter Platforms:

• • Revue: Acquired by Twitter, Revue offers similar services allowing writers to publish and monetize newsletters.
  • Ghost: An open-source platform that focuses on professional publishing. It’s known for its simplicity and flexibility.
  • Mailchimp: While primarily an email marketing service, Mailchimp also offers features that could be used for newsletter monetization.
  • TinyLetter: Owned by Mailchimp, it’s a simpler platform primarily used for personal newsletters.
  • ConvertKit: A platform that offers email marketing services for creators, including paid newsletters.

2. Broader Content Monetization Platforms:

• • Patreon: Known for allowing creators to get paid directly by their fans through subscriptions, memberships, and per-piece payments.
  • Medium: Offers a partner program where writers can earn money based on reader engagement with their articles.
  • Ko-fi: A platform where creators can receive donations and sell subscriptions or products.

Features

What are my competitors’ unique features? This prompt can help founders with product development and positioning:

Create a table listing the unique features of each competitor and pricing.

Here’s ChatGPT’s response. I’ve repurposed the table for this article. Always ask ChatGPT for the date of its data if it doesn’t provide it. In my test, the response was based on the April 2023 update.

Platform	Unique Features	Pricing
Revue	Integration with Twitter, allowing for easier sharing and audience building on the social platform	Free; Twitter takes a 5% cut of subscription revenue
Ghost	Open-source with advanced customization options; SEO and membership features integrated	Starts at $9/month for the hosted version; free if self-hosted but requires server costs
Mailchimp	Extensive email marketing tools; detailed analytics and A/B testing capabilities	Free tier available; paid plans start at $9.99/month
TinyLetter	Simplistic design and functionality focused on personal newsletters	Free; limited to 5,000 subscribers
ConvertKit	High deliverability rates; strong automation and tagging system for segmentation	Free tier up to 1,000 subscribers; paid plans start at $29/month
Patreon	Membership tiers for different levels of content access; strong community-building tools	5% to 12% of monthly income plus payment processing fees
Medium	Large built-in audience; earnings based on reader engagement rather than subscriptions	Free to publish; readers pay $5/month or $50/year for unlimited access
OnlyFans	Known for adult content but also used for other types; direct messaging with subscribers	Free to create an account; OnlyFans takes a 20% commission
Ko-fi	One-time support options (‘buy me a coffee’), no platform fee for donations	Free; Ko-fi Gold membership at $6/month for extra features

Audiences

What are my competitors’ target audiences? ChatGPT is very helpful for that type of analysis, in my experience. My prompt:

Go to each competitor’s site and analyze its primary audience. Create a table showing the competitor, the primary audience, and the site elements and pages that indicate the target audience.

Here’s the result, which, again, I’ve repurposed.

Competitor	Primary Audience	Site Elements Indicating Target Audience
Revue	Freelancers, Twitter users	Integration with Twitter, simplicity in newsletter creation, memberships and paid subscriptions.
Ghost	Independent journalists, professional publishers	Open-source technology, focus on professional publishing, advanced creator tools, audience growth capabilities, and integration options
TinyLetter	Individuals preferring simplicity	Basic design tools like a standard email client, option for HTML customization, simplicity and ease of use for personal or small-scale use
ConvertKit	Wide range of creators (coaches, authors, podcasters, musicians, YouTubers)	Tools for audience growth, email automation, monetization, testimonials from various creators, broad appeal across different creative fields
Patreon	Diverse content creators (video makers, podcasters, writers, musicians, educators)	System for creators to offer exclusive content/benefits for financial support, focus on diverse content types, and sustainable income stream for creators

Responding to Competitors

Should I reposition my site based on competitive research? Here’s my prompt:

What should I do on my site to attract competitors’ audiences? Analyze competitors’ sites for the most effective tactics.

ChatGPT identified powerful tactics for Substack:

• Content variety: Showcase a diverse range of content that appeals to creators across different fields like coaching, writing, podcasting, music, and YouTube creation.

• Creator tools: Offer robust marketing and automation tools tailored for creators. These could include customizable landing pages, email marketing tools, and audience segmentation features.

• Monetization features: Highlight options for monetizing content, such as through digital product sales, paid newsletters, and memberships.

• Community building: Focus on features that help creators build and engage with their audience, like advanced email marketing and automation capabilities.

• Creator success stories: Share success stories or testimonials from various creators to demonstrate the potential of your platform for their creative and financial growth.

Weaknesses

What are my competitors’ weaknesses? I chose one of those companies, which I’ll call “Example” for this post, as a test. Here’s that prompt:

Research Example’s reviews and identify gaps Substack could address. What are the common complaints of Example’s customers?

ChatGPT searched Bing for several minutes before responding:

• Pricing Structure: Some users find Example’s subscription plans to be expensive, especially as their subscriber count grows. A more cost-effective pricing structure or clearer value for the cost could be an attractive alternative for users.

• Complexity for Beginners: While Example has evolved to offer a wide range of features, this has led to increased complexity. Users who preferred the platform’s original simplicity might be looking for a more straightforward, user-friendly option.

• Deliverability Issues: There are mentions of challenges with email deliverability. Ensuring high deliverability rates and providing transparent metrics could be a key selling point.

• Limited Free Plan Features: The recent reduction in features available in the free plan has been a point of contention. Offering a more generous free plan could attract users who feel constrained by these limitations.

• All-in-One Marketing Features: Some users feel that while Example offers an all-in-one marketing platform, the features are not as robust as they would like. Enhancing specific functionalities or offering more integrated solutions might appeal to these users.

• Customer Support: Improving customer support and providing more personalized assistance could address concerns from users who have had less than satisfactory experiences with Example’s support.

We’re rolling out genuine use cases for AI and crypto each day this week — including reasons why you shouldn’t necessarily believe the hype. Today get two for the price of one: Blockchain based AI marketplaces, and financial analysis.

It may not seem like the most exciting use case blending AI and crypto, but both Near co-founder Illia Polosukhin and Framework Ventures founder Vance Spencer cite blockchain-based marketplaces that source data and compute for AI as their top pick.

AI is an incredibly fast-growing industry requiring ever-increasing amounts of computing power. Microsoft alone is reportedly investing $50 billion into data center infrastructure in 2024 just to handle demand. AI also needs enormous amounts of raw data and training data, labeled into categories by humans.

Polosukhin believes decentralized blockchain-based marketplaces are the ideal solution to help crowdsource the required hardware and data. 

“You can use [blockchain] to build more effective marketplaces that are more equal,” he tells Magazine, explaining that AI projects currently need to negotiate with one or two big cloud providers like Amazon Web Services. Still, it’s difficult to access the required capacity due to a shortage of Nvidia’s A100 graphical processing units.

Spencer also cites blockchain-based marketplaces for AI resources as his current number one use case.  

“The first one is sourcing actual GPU chips,” he says. “Where there’s a big shortage of GPU chips, how do you source them [without] actually having a network that sources and provides and bootstraps a market?” 

Spencer highlights Akash Network, which offers a decentralized computing resources marketplace on Cosmos, and Render Network, which offers distributed GPU rendering.

“There are some pretty successful companies that actually do it at this point that are protocols.”

Another example of a decentralized marketplace offering cloud computing for AI is Aleph.im. Token holders in the project are able to access computing and storage resources to run projects.

Libertai.io, a decentralized large language model (LLM) is being run on Aleph.im. While you might think decentralization would slow an AI down to the point where it’s unable to function, Aleph.im founder Moshe Malawach explains that’s not the case:

“This is the thing: for one user the whole inference (when you generate data using a model) is running on a single computer. The decentralization comes from the fact that you get on random computers on the network. But then, it’s centralized for the time of your request. So it can be fast.”

Another blockchain-powered AI marketplace is SingularityNET, which offers various AI services — from image generation to colorizing old pictures — that users can plug into models or websites.

An emerging blockchain based AI marketplace that Spencer is super excited about is tokenizing and trading AI models. Framework has invested in the Super Smash Brothers-like fighting game AI Arena, where users train AI models that battle each other. The models are tokenized as nonfungible tokens and can be bought, sold or rented. “I think that’s really cool,” he says. “It’s interesting having the crypto native monetization, but also ownership of these models.”

“I think one day, probably some of the most valuable models — some of the most valuable assets on-chain — will be tokenized AI models. That’s my theory, at least.”

Don’t believe the hype: You can currently source components, data and compute via traditional Web2 marketplaces.

Bonus use case: Financial analysis

Anyone who has tried to interpret the ocean of data produced by on-chain financial transactions knows that although it’s one thing to have an immutable and transparent record, it’s quite another to be able to analyze and understand it.

AI analytics tools are perfectly suited to summarizing and interpreting patterns, trends and anomalies in the data, and they can potentially suggest strategies and insights for market participants.

For example, Mastercard’s CipherTrace Armada platform recently partnered with AI firm Feedzai to use the technology to analyze, detect and block fraudulent or money laundering-related crypto transactions across 6,000 exchanges.

Elsewhere, GNY.io’s machine learning tool attempts to forecast volatility of the top 12 cryptocurrencies and its Range Report uses ChatGPT-4 to analyse trends and buy/sell signals.

But can AI help with traditional markets, too? That’s the hope of Bridgewater, which will launch a fund next year from its new Artificial Investment Associate (AIA) Lab that aims to analyse patterns in financial markets so it can make predictions for investors to capitalize on.

Previous attempts to do this have produced lacklustre results — with a Eurekahedge index of a dozen AI driven funds underperforming the its broader hedge fund index by around 14 percentage points in the five years until 2022.

This is mainly due to the issues involved with feeding in the large amounts of accurate information required.

Ralf Kubli, a board member with the Casper Association, believes AI can revolutionize traditional finance — but only if it combines blockchain records with rigorous standards to ensure the information fed to the models is comprehensive and accurate. 

For years, he’s been advocating for the finance industry to adopt the Algorithmic Contract Types Universal Standards, or ACTUS, created in the wake of the Global Financial Crisis, which was partly caused by complicated derivatives where no one understood the liabilities or cash flows involved. He believes on-chain standardized data will be essential to ensure trust and transparency in model outputs.

“Fundamentally, we believe that without blockchain, AI will be quite lost,” he tells Magazine. “Imagine you’re going to invest in an AI company, and you’re updated every three months about the progress of their LLMs, right? If you cannot verify what they fed into the model, you have no way of knowing whether they are making any progress.”

He explains blockchain guards against companies fudging their results, “and the past would indicate that […] there’s so much money, they will fudge about what’s going on.”

“AI, without this assurance layer of the blockchain — what happened, when, where, what was used — I think will not be effective going forward.”

He says that combining the two will give rise to new predictive abilities.

“The hope for AI for me going forward is that the prediction models become much more powerful and behavior can be much better predicted,” he says, pointing to credit scores as an example.

“AI used in the right way could potentially lead to much more powerful prediction models, which would mean that certain people who currently cannot get credit — but would be creditworthy — can obtain credit. That’s something I’m very passionate about.”

Don’t believe the hype: AI’s predictive abilities have been shown to be poor at best so far, and trusted and reliable data that’s not recorded on blockchain can be useful input for AI analysis.

Also read:

Real AI use cases in crypto, No. 1: The best money for AI is crypto

Real AI use cases in crypto, No. 2: AIs can run DAOs

Real AI use cases in crypto, No. 3: Smart contract audits & cybersecurity

Real AI & crypto use cases, No. 4: Fighting AI fakes with blockchain

Bitcoin (BTC) sought to rematch 18-month highs into Nov. 21 as order book activity gave one analyst a sense of deja-vu.

Whale games conjure Bitcoin’s Q1 2023

Data from Cointelegraph Markets Pro and TradingView showed BTC price momentum building to top out at $37,770 the day prior.

Now circling $37,400, Bitcoin remained in a range, which had also characterized the second week of the month.

For on-chain monitoring resource Material Indicators, however, the market was more akin to Q1 this year — the period which marked the start of Bitcoin’s recovery from post-FTX lows.

Analyzing order book data, it suggested that a major liquidity provider which it informally called the “Notorious B.I.D.” at the time could be shaping bid support once again.

Specifically, bid liquidity had come and gone at $33,000 “7 times in the last 30 days,” it told X subscribers.

“I can’t confirm whether this is the entity I named Notorious B.I.D. back in Q1, but I can tell you we’ve seen this game played before.”

An accompanying snapshot of BTC/USDT liquidity also showed sellers lining up at and immediately below $38,000.

Among whales, it was the largest order class — between $1 million and $10 million — which was the only active cohort, with others unanimously decreasing exposure through the week.

Commenting on the situation, Material Indicators co-founder Keith Alan argued that the entities behind the buy orders could be more organized than merely large-volume speculators.

The bid wall at $33k disappeared AGAIN and Brown MegaWhales bought resistance at the local top AGAIN.

If you think MegaWhales have an issue with timing, re-read the thread I shared from @MI_Algos.

No telling how long they keep this game going. Of course, I have my theory about… pic.twitter.com/sEZuvSgWIs

— Keith Alan (@KAProductions) November 20, 2023

“Swift breakdown” could follow tap of $40,000

Forecasting what could come next, meanwhile, Michaël van de Poppe, founder and CEO of trading firm Eight, refused to take $40,000 off the table.

Related: 70% of BTC dormant for a year — 5 things to know in Bitcoin this week

“Bitcoin continues to push higher and higher. Making higher lows, and attacking the resistance for the fourth time,” he commented on overnight events.

“Wouldn’t be surprised with a breakout upwards to $40K and then a swift breakdown again. Keep on buying the dips!”

Popular analyst Matthew Hyland cautioned that relative strength index (RSI) could be at risk of printing a bearish divergence with price should the latter fail to pass current 18-month highs just below $38,000.

At the time of writing, bulls were still unable to summon the required momentum.

#Bitcoin still all going to plan

Price and RSI are moving up

Both will need to put in higher highs to prevent any opportunity at bearish divergence

Will continue to update this situation: pic.twitter.com/1XxPhiDd28

— Matthew Hyland (@MatthewHyland_) November 21, 2023

This article does not contain investment advice or recommendations. Every investment and trading move involves risk, and readers should conduct their own research when making a decision.