SmileDirectClub: a True “Megatrends” IPO with Good Alternative Data Metrics

The US IPO market continues to be very healthy, and we continue to publish our notes here on some of the more interesting companies coming to market. Today’s post focuses on SmileDirectClub (proposed ticker SDC) but also do check out our recent posts on Chewy, Slack, WeWork, Beyond Meat, and Pinterest.

You might already be familiar with Invisalign, (by Align Technology, a company with an almost twenty year history in the public markets), the clear plastic “braces” that have grown in popularity tremendously over the years for treatment of certain cases of malocclusion. From a client’s perspective, the main difference between ALGN and SDC is that SDC’s service does not require in-person visits to an orthodontist, and SDC is lower cost. Looking at ALGN’s most recent 10-K filing, we can see that the company has grown revenue at a 27% CAGR since 2014, and finished 2018 with almost $2 billion in revenues.

There is a more recent crop of entrants in the clear aligners space, the most notable of which is SmileDirect. We read the S-1 and the S-1/A with great interest because SmileDirect is at the intersection of several mega-trends. This is not hype: we really mean this. SmileDirect has both the sales growth and, by now, the sales volume to prove it. Revenue grew 7x from 2016 to 2017, then almost 3x’ed from 2017 to 2018, and is now on track to more than double in 2019. Patients (or, if you prefer the company’s more modern word choice, “members”) are now at over 700k cumulatively. 

By way of comparison, it took ALGN from 2010 to 2014 double from $387 million in revenues to $761 million, while it looks like it will take SDC just one year to double from roughly the same starting point of approximately $400 million in revenues. 

SDC’s explosive growth has been, in our view, powered by true megatrends. These megatrends are:

  • Direct to Consumer (DTC) with subscription and omnichannel characteristics
  • Healthcare delivery innovations
  • Healthcare access and affordability  
  • Beauty

And SmileDirect appears to be winning across the board with a vertical integration of advanced technology, in-house financing, high skill offshoring/regulatory arb, and good marketing.  

The customer journey at SDC begins with either a visit to one of 300+ “SmileShops” (co-located at CVS and Walgreens in the US; also UK, Canada, PR, Australia) for a scan, or with an at-home impressions kit. The company staff in Costa Rica (orthodontists and technicians) then prepares a treatment plan, which the customer approves, with the final approval (prescription) happening through a state-licensed US-based orthodontist. The sequence of aligners is shipped at once from a US facility (one in TN, one being built in TX), with periodic check-ins required. The major benefits, as described in the S-1, are (1) lower cost (list price of under $2,000 vs. $5,000-$8,000); (2) expanded access to treatment through teledentistry (no office visits; the company also states that fewer than 40% of US counties have orthodontists); (3) shorter time frame for treatment (5-10 months vs. 12-24 months, though it is unclear how much of this is due to case specifics), and (4) captive financing (with recently expanded “in network” access with two major US insurers). 

We see the “megatrends” every step of the way: DTC infrastructure enables direct relationships, omnichannel presence increases reach, and, obviously, the product/service is 100% personalized. The combination of DTC and lower cost, high skilled operations expand access by lowering cost (though two state dental boards, in AL and GA, have taken issue with the latter- we see it as a bit of a regulatory arbitrage to have the last “touchpoint” done in the US-, and SDC is currently suing both entities). There is quite a bit more from the management presentation on the total market potential and other aspect on Retail Roadshow (link generally available prior to the actual offering). The management story is very interesting: the CEO David Katzman has a long history of involvement in disruptive services (Quicken Loans being the most famous but also a direct lenses business sold to the leader in that space, and an earlier venture acquired by Home Depot). The subscription element is the growing retainers business post-treatment (a substantial percentage of patients are people who had braces years ago but whose teeth moved back). 

The in-house financing part is also an interesting aspect of the operation: the company offers a “no credit check” financing option at 17% APR ($250 downpayment, which covers the cost of the aligners, and then $85 monthly payments over 24 months). The default rate is under 10%. The most recent data is that 65% of the customers use SmilePay, indicating both the importance of having an affordable and transparent option for discretionary procedures. The CEO on the roadshow said that prior experience with third-party financing was negative (too high drop-offs). The complications around the consumer financing regulation are an additional “moat” for the model. 

We were also interested in the marketing aspect of this remarkable growth story: the company says that it has around five million unique visitors to its website every month, and that it is able to convert about 1% of them to new customers, up from 0.5% in 2016. The company has also been improving its appointment show rates at the SmileShops and the acceptance of the impression kits. The company also lists over 300,000 followers on Instagram and over 500,000 likes on Facebook, as of June 2019. These numbers as of right now are over 360,000 followers on Instagram (20% growth in three months) and 531,000 Likes on Facebook. The company also boost very high review ratings (4.9/5.0), and 57 Net Promoter Score (extraordinarily high, on par with Zappos, per the roadshow linked above). 

Since we incorporate alternative data sets very heavily in our platform (see our recent webinar and white paper on the topic), we were interested in seeing how the data looks. 

We are seeing very good long-term trends for the broad search trends for clear aligners, as a search topic (a broader collection of searches, versus a specific term). This is a valid signal as aligners are a high investment purchase, both in terms of money and in terms of time (or, as the company calls it, a “highly considered purchase” with long lead cycles: the roadshow presentation mentioned that a lot of customers are 7-12 month leads). We can also see the January spikes in search interest, similar to fitness interest and other self-improvement topics. (Interactive chart link

 

The customer journey might start with broad searches but then a lot of the research is done on the companies’ websites. We pulled the Alexa data for SDC, ALGN, as well as the DTC competitors that SDC lists in the S-1: CandidCo, SnapCorrect and SmileLove. We can clearly see that overall industry web traffic has been growing, and that SDC is now bigger than ALGN. We are showing 30-day moving averages (Interactive chart link)

 

Perhaps most interesting to us is the web traffic “market share” that SDC has vs. the incumbent leader ALGN build from the overall chart above (what percentage of the industry traffic goes to the two major players). We can see that SDC is now consistently capturing more traffic vs. ALGN, likely indicative of future real share growth. (Interactive chart link

 

We fully expect that this offering will be very popular given the defensible growth characteristic of the business, and the current investors’ relaxed attitude around governance/related issues. (Not the topic of this piece, but SDC is a JOBS Act IPO, with multi-class shares, classified board, numerous related party transactions including a Tax Receivable Agreement, underwriter conflicts, corporate structure, and quite a bit more). 

New call-to-action

Which Retailers Are Winning This “Back to School” Season? Combining Document Search and Alternative Data to Find Out

Our first step to analyzing how retailers are doing during this “Back to School” season is to use our industry-leading Document Search to find out which retailers are talking about “Back to School” in the first place. If keyword mentions appear in filings or in transcripts, then we know that we should be taking a closer look at that company. 

We start in our Document Search without tickers (since we want keep the search broad to firstly see who mentions “back to school”). We combine our in:CF (in-filings) and in:TR (in-transcript) search for exact match “back to school.” We can also see our machine learning-suggested synonyms as well, though here we are not going to use them. 

We add two filters: one is an industry filter (Consumer Discretionary and Consumer Staples), and the other is a geographic filter (US). 

In our next step, we create our “Back to School” retailers watchlist by simply saving all companies that have positive hits in our search. We started with a fairly broad theme that is now confined to a watchlist with specific companies on it. 

In our next step, we name our Back to School watchlist, configuring any alerts that we would like to receive, and saving the watchlist with alerts preferences. 

In our next step, we brought in our just-created Back to School list in our customizable Dashboard, where we are looking at a few things related to our composite alternative data index. (Watch this recorded webinar to find out how our alternative data index takes several sets, calendarizes them properly to the reporting periods, and then compares the “index” to the consensus estimates).

First, we see which is the optimal metric against which the index works best, based on past performance. Since these are retailers, we can see that comparable store sales, a standard KPI for the industry, works better than revenue for some. Second, we see the R-squared that our index has against that optimal metrics: a higher number here indicates a higher predictability. 

We dig deeper by checking the individual dataset metrics on a monthly basis for YoY changes (in this case, we are showing monthly YoY percentage change in search trends and page views) along with the earnings dates.

We see that there 18 retailers reporting in the next few days (the week of August 26, 2019, and the week of September 02, 2019). They are: CAL, BNED, TIF, EXPR, FIVE, TLYS, SCVL, AEO, GCO, BBY, BURL, DBI, ANF, DLTR, PVH, ZUMZ, FRAN, and VRA. Since these retailers’ fiscal year typically ends at the end of January (vs. the standard December for the majority of publicly traded companies), the Q2 numbers are for the quarter ending in July. So the “back to school” period is somewhat split. But investors do expect QTD color for Q3, as well as guidance updates. Since the Sentieo team has decades of buyside experience (all product managers are former buyside and/or sellside analysts), we know that we can eliminate TIF, BNED, and FRAN from the list. TIF, a high-end jewelry retailer, is not really driven by BTS, while BNED and FRAN are “special situations” currently. 

With our slimmed-down, “actionable” list of 15 stocks, we took a look at what our composite index looks like YoY (used for the more predictive metric, revenue or comparable store sales growth).  

We see the potential for strong overall YoY revenue growth in FIVE, PVH, DBI, AEO, CAL, ZUMZ, and VRA. We see the best potential for comparable store sales growth for BBY, BURL, SCVL, and DLTR. 

Taking this a step further, we can look at past performance by adding the R-squareds to our list (higher = more predictive). Our confidence is highest in the YoY revenue growth performance from FIVE and AEO, and for comps, in BURL. 

To find out more on how you can compare the alternative data composites against the analyst consensus numbers, please see our white paper and webinar from a few weeks ago, or request a trial with a product specialist

New call-to-action

Just How Unusual Are the Related Party Transactions Disclosed in The We Company’s S-1 Filing?

To find out, the Sentieo team took a look at other recent high profile IPOs to compare against what we saw in The We Company’s expansive 800+ page S-1 filing. The document also contains 198 separate tables. Inside the filing, the Company (proposed ticker: WE) spends ten pages on discussing various transactions with “related parties.” Contrary to widespread understanding, related parties are not limited to just insiders and large owners. In this case, the underwriters of the equity IPO are also considered related parties, since there are multiple non-IPO business transactions that have occurred prior to the filing. If you are interested in finding out more about the regulations, there are extensive SEC publications regarding these disclosures (for example, there is a 436-page PDF published by the Commission on the topic).

Part of what we see is attributed to the fact that as a real estate company, WE uses bank financing. Another aspect is that as a remarkably fast growing company in the physical world, the company has needed trusted JV partners in different geographies.

WE has disclosed various transactions with four “levels” of insiders: the founder, Adam Neumann and his family, its executives, its pre-IPO investors, and its banks. In fact, “related party” or “related parties” is mentioned 110 times in the document.

In the first group, WE has business relationships with the founder across several dimensions: it leases a small number of buildings from him, there are unusual supervoting stock, succession, charitable giving, real estate, and compensation arrangements. There are several family members employed or doing business with the firm. The founder was paid almost $6 million for the renaming of the company (since he personally had a company called We Holdings), and he has borrowed several times from the company, and separately from its offering underwriters.

WE also disclosed related party transactions with several executives, including loans and bonuses that were used to repay these loans.

SoftBank and Hony are investors in WE but are also partners for WE in its various Asian joint ventures.

The IPO underwriters (a collection of bulge bracket banks) also have several “related party” disclosures: ownership of preferred stock, loans to the company, as well as personal loans to the founder: almost $500 million secured either by WE stock or by personal properties.

So how unusual is this level of related party transactions in recent high profile IPOs? We took at look at Slack, Uber, Lyft, Chewy, Pinterest, Levi Strauss, and Zoom Video to get an idea. 

In Slack’s filing, we see a few mentions. There have been several rounds of convertible preferred financings and executives selling shares. There have been transactions with Square (since the Square CFO is on the Board of Slack, she’s a related party), some content partnerships with the wife of the CTO and the former domestic partner of the CEO, and the son of a BOD member works at the company. The VC investors are also partners with Slack in an “in house” VC fund. (We dug deep into Slack’s business model back in May).

Uber, like Slack, has had several rounds of convertible preferred financing. Its executives, like Slack’s, have had pre-IPO liquidity events with company involvement. It has a co-investment with Softbank (and Toyota) in an AV venture. Uber has a relationship with Google Maps, Google’s ad business and Google Pay, all owned by Alphabet, an investor. The daughter of an executive is employed at the company. There are a few other bits and pieces, like their relationship with DiDi.

Lyft’s related party transactions are almost a carbon copy of these at Uber: investors with convertible preferreds, and business relationships with several related parties, such as Google, General Motors and Rakuten. (Our five big AV takeaways from Uber’s and Lyft’s filings are written up here).

Chewy, the fast-growing online pet product retailer, was mostly owned by pet product physical retailer PetSmart. Its related parties disclosure is relatively plain, and almost entirely focused on its operational relationship with PetSmart: purchasing, product, tax and governance matters, not unusual in the case of subsidiary IPOs. (Our read of Chewy’s full IPO filing is here).

Pinterest, similar to the tech companies described above, has disclosures around its relationships with its VC investors, and there is one family member of an executive employed in a non-executive function. (We wrote a very long post analyzing Pinterest after the IPO).

Beyond Meat disclosed a consulting agreement with its Chairman and an advisory contract with a Board of Directors member. There was a one-time consulting agreement with another BOD member (the former CEO of McDonald’s), and loans to BOD members that were repaid in 2018. (We recently dug around Beyond Meat’s secondary offering documents).

Levi Strauss & Co. has a fairly straight-forward 2-page disclosure: the descendents of the founder have certain rights as shareholders, some executives have sold stock back to the company, and there is some overlap between the executive team of the company and that of the Levi Strauss Foundation, to which the company also donates. There is one former BOD relative employed at the company.

Similar to LEVI, Zoom has a short disclosure doc: relationships with the VC investors, its founder had sold some stock to a fund and had a loan in 2015-2016, and a BOD member is from Veeva, which is also a small client.

It is fair to say that WE’s relationships with its related parties go well above and beyond what we have seen in the other recent high profile initial public offerings. The most common are: governance arrangements with pre-IPO VC investors, followed by ordinary course of business relationships with investors such as Google (it is hard for a consumer-facing business to avoid working with Alphabet properties), and finally, cases of founders and executives getting some liquidity for their equity stakes over the years.

New call-to-action

Obscure Berkshire Hathaway Filing Reveals What Warren Buffett Thinks About Kraft Heinz

Berkshire’s investment in Kraft Heinz has not gone smoothly. After taking Heinz private together with private equity investor 3G in 2013, Berkshire invested additional funds in the takeover of Kraft Foods in 2015, and was ready to finance a quickly-withdrawn $143 billion offer for Unilever.

Things have gone south for KHC recently. The company’s stock price and valuation have shrunk considerably over the last two years versus that of its peers. We can see KHC’s EV/NTM EBITDA multiple (in thick red below) starting at the top of its peer group two years ago, but recently declining to very the bottom compared with other US food companies (interactive chart link). We do expect the multiple to move up somewhat over the next few days as analysts adjust their estimates after the call.

 

KHC also had to delay its financial reporting this year due to certain actions by former employeesthat led to small restatements, and more notably, the company took a $15 billion write-down of brand values and cut its dividend in February of this year. In the most recent call on August 8, 2019, the company, now with a new CEO from AB In-Bev, did not provide guidance, took additional impairments, and warned of future impairments.

The travails at KHC are a topic of increasing concern to Berkshire Hathaway investors. The number of mentions of Kraft on the most recent shareholder meeting more than tripled versus last year to 27, up from just 8 in 2018.

Buffett himself did admit that Berkshire overpaid for Kraft but still thinks KHC is a “wonderful business.”

 

While getting color from the transcripts is nice, we were also interested in what is actually in the Berkshire filings, so we redlined the second quarter 10-Q filed with the SEC on August 5, 2019 against the Q1 version of the document. We saw a lot of new language around KHC.

What we’re seeing is a lower fair value of the investment (easily observable, since KHC is publicly traded). The carrying value was reduced because of the KHC financials’ restatement. We also see some puts and takes around the KHC YTD filings.

Most interesting to us was the inserted paragraph at the bottom; Berkshire reviewed KHC for impairments, and as of June 30, 2019, decided against it.

 

But Why?

The answer comes in a more obscure SEC filing, called CORRESP for Correspondence. CORRESP and UPLOAD are two forms of formal communication between the Commission and the filers. When a letter is directed from the SEC, it appears in filings as UPLOAD, and when the filer responds to the regulator, it is a CORRESP. 

Berkshire filed two UPLOAD and two CORRESP forms on July 24, 2019, though the exchange between the company and the regulator had taken place in May and June. 

The SEC was interested in how Berkshire was accounting for Kraft Heinz in the Q1 2019 10-Q filing. 

 

And here is how Berkshire responded in great detail to the SEC: KHC’s stock price decline and the length of this decline was not substantial enough. Also, the operating results, while currently poor, will be better (divestitures, brand power, reduced but not eliminated dividend)

 

On the following page, we see more information related to how Berkshire thinks about KHC: there are no plans to sell the stock at any time, and the KHC restatements are immaterial. 

 

Given Berkshire’s long involvement with Heinz, and then with Kraft Heinz, including Board of Directors representation, and its continuous investments in the space, we view these disclosures as material: Warren Buffett still thinks KHC is a long-term holding position that will recover.

New call-to-action

Disrupting Transcripts: Spike In “Deflections” on Tesla’s Latest Call

In our final earnings week blog post discussing our new, machine learning-based transcript Smart Summary™, we’re taking a look at the electric car maker, Tesla. The company reported earnings and held its regular quarterly call after market hours on Wednesday, July 24, 2019. The stock dropped immediately upon the results release, and continued dropping during the call and into the next day.

While every quarter at Tesla has many puts and takes (like international shipments, tax credits, specific model volumes), what really stood out for us when we applied the Smart Summary™ was the really serious increase of “deflection” instances quarter over quarter. Our tweet on the topic got almost 10,000 views in a few hours:

 

So what is “deflection?”

Our new transcript Smart Summary™ tool has two underlying mechanisms. One is based on a specially trained machine learning system in which we, mostly former buysider product managers, trained the system to parse and classify sentences into a large training data set across industries and companies. This tool automated what we used to do during earnings season, and will only get better as our users submit direct feedback. Transcript Classifications are not mutually exclusive; a sentence might often be a Guidance and a KPI sentence at the same time. 

The second mechanism powering Smart Summary™ is natural language processing. We have had overall sentiment reports for management and analyst teams, and keyword surfacing applied to transcripts in the product for a long time. What we’re introducing with the Smart Summary™ is the scoring of specific sentences (positive/neutral/negative) across all Classifications (so a sentence might be “positive Guidance” and “positive KPI” at the same time). The other NLP application is what we call “deflection.” We dug through the academic literature and identified a specific lexicon that has shown to lead to future negative corporate events. 

Looking at the Deflection summary view in the Tesla call, we see quite a bit of the usual enthusiasm and grand visions from CEO Elon Musk.

We see the recently appointed CFO discussing the challenges in the quarter-to-quarter business:

It was most interesting to us that the remarks by the outgoing CTO (a surprise departure) were also picking up as deflection:

The final statement on the call by the CEO was also marked as deflection: will Tesla beat the industry economics?

To find out how Sentieo can help with your process, please get in touch

New call-to-action

Disrupting Transcripts: Short Video Example on UPS

Last week, just in time for earnings season, we released Sentieo’s machine learning-based transcript Smart Summary™ feature. In short, we automated what we used to do as buyside analysts: reading through transcripts and classifying information.

This week, we’ve looked at the newest transcripts from Goldman Sachs and Haliburton in detail. Yesterday, we shared an in-depth video discussing Whirlpool: from redlining the 8-K, to looking at the stock price action post-call, to its Smart Summary™. 

Today’s video is shorter, as we only focus on the Smart Summary™ aspect and we discuss UPS. We were able to extract the important information in about 2 minutes.

The Smart Summary™ is one of two major ML-based product releases we had this month: take a look at our synonym suggestion tool as well. Your searches can be a lot more productive with this dynamic addition to our existing large synonym/acronym dictionary.

If you are ready to test out our platform, please get in touch.

New call-to-action

Disrupting Transcripts: A Smart Summary™ Video Tutorial

This week we’re showcasing our new, machine learning-based transcript Smart Summary™, an entirely new way of reading — and more importantly, summarizing — transcripts

Yesterday, we looked at Halliburton’s transcript Smart Summary™In today’s post, we’re sharing a video that covers Whirlpool (NYSE:WHR), a “classic” industrials company. We review the earnings 8-K, discuss the positive after-market reaction to the guidance increase, and then we dive into the transcript to see why the stock actually declined after the call. 

To try using Smart Summary™ in your own research workflow, sign up for a custom demo.

Disrupting Transcripts: How We Used Sentieo’s Transcript Smart Summary™ to Review the Halliburton (HAL) Call

Oilfield services provider Halliburton (NYSE:HAL) is the first installment in this week’s Smart Summary™ showcase. We are applying our newly released machine learning-based tool to improve our own reading while saving time. Below, we will highlight how we picked out the critical pieces of information on the call in just a handful of minutes. 

If you haven’t read this feature’s announcement post, here’s a recap. Smart Summary™ is a one-click application of machine learning that “slices” transcripts in several ways. One of these slices is a broad Classification, like “Guidance” or “KPIs. (See 1 below).

The second slice (2) is based off NLP-powered sentiment (green and red labels). The third application is based on surfaced Key Terms: products, brands, and geographies (3). The fourth and most innovative application is the removal of the chronological flow all together; sentences are sorted in a table view mode, and can be ranked by “signal strength.”(4) 

(1) (2) This is what the clickable Classifications look like for HAL’s transcript:

(3) Top NLP-surfaced Key Terms are clickable as well.

(4) Clicking the Table Icon in the upper right will open the sortable sentence Table View. (Click on image to zoom in).

With this in mind, here is what we are seeing as key pieces of information in HAL’s transcript.

Free Cash Flow has been and will continue to be positive. This is really good news given the FCF challenges in the energy industry:

Directly related to FCF, HAL is cutting back on capex and is focusing on margins:

Increased activity in several regions led revenue growth in the quarter, while the overall outlook is optimistic:

Switching from the full transcript view to the summary view for the Guidance classification, we see the summary at the end of the call: guarded optimism and focus on margins and capex. 

We complete the final review of the transcript using Table View: the non-chronological way to extract information from transcripts. We can see how key sentences on the topics highlighted above are picked up by NLP. Readers can sort sentences along several categories. 

In terms of Guidance “loading,” we see Free Cash Flow ranked highly multiple times:

Ranked purely on sentiment, we can see that the overall business did well in the quarter across several geographies:

Ranking for Products and Markets, we see new product discussions as well as the pricing signals.

Investors can also easily pick up the negatives in the results and in the outlook: large legacy frac fleet, soft pricing seen by competitors, some segments might see revenue declines. 

Reading non-chronologically does not mean reading out of context. Simply click on the Context link to see the phrase within context. 

The Table View is also available for the NLP-surfaced Key Terms. In one glance we can see whether these terms are used more or less quarter-over-quarter, and by whom (analysts vs. management). We see how prominently “North America,” “capex,” and “Free Cash Flow” are featured. An added time-saving convenience is that these Key Terms are click-through: clicking on one will search all HAL transcripts for that term, so you can get immediate historical context in seconds. 

Here we have clicked on Capex, and we can see highlights in the most recent transcript: note how Sentieo’s synonym search picks up various forms of the term.

To learn more about how using the latest ML-based tools can help you and your team be more productive, please get in touch with us

 

New call-to-action

Disrupting Transcripts: Applying Sentieo’s Smart Summary™ During Earnings Season

After last week’s release of Sentieo’s machine learning-based Smart Summary™ for transcriptsthis week we will be highlighting exactly how to use this powerful new feature to ensure that you don’t miss important information this earnings season, and that you also save time.  

The Smart Summary™ tool classifies a document’s language based on several categories such as Guidance, KPIs, and company-specific key terms (like product names) into a convenient, time-saving format. Further, it applies an NLP sentiment filter to highlight positive and negative language. 

Smart Summary™ is the latest machine learning and natural language processing-based tool released by Sentieo this year. We’ve also released a dynamic synonym suggestions feature for Document Search based on our own, internal synonym search tool. Additionally, we added company-specific autocomplete suggestions to our search. And earlier this year, we rolled out Table Explorer, a flexible and auditable tool that identifies, chains and visualizes tables in SEC filings. 

During the next few days, we will be selecting and publishing our highlights from current transcripts to show how effective Smart Summary™ can be in your research workflow. (Stay tuned).

For example, if we look at the transcript from the Goldman Sachs call last week (below), we can pick up essential corporate and macro information (color-coded as needed), under the Financials and KPIs classification. Scrolling down in the Smart Summary™, we see record assets under supervision: good news in green, versus slower Chinese GDP growth in red, a couple of paragraphs down. The full context is right there as well. 

In addition to viewing by Classification group, users can quickly scroll through all positive and negative highlights, regardless of Classification. 

In the Key Terms field, we catch up on Marcus, Goldman’s growing consumer banking franchise. We can see a mix of positive and neutral statements. 

For the next few days, the blog will be highlighting exactly how we’re applying this powerful new functionality. To try it yourself, please get in touch

New call-to-action

Disrupting Transcripts: Introducing Sentieo’s Smart Summary™

Just in time for earnings season, Sentieo is releasing Smart Summary™, a whole new way to read transcripts. 

We all know the problem that analysts and portfolio managers face four times per year: multiple companies reporting on the same day, which creates impossible scheduling conflicts, work overload, and forced prioritization, which then leads to costly missed information.

Analysts might dial into one or two consecutive high priority calls, and then go on to read another four to eight transcripts later in the day, depending on coverage. These transcripts are always read chronologically, starting with the boilerplate language on top, and ending with the analyst questions. 

Until now. 

With Sentieo’s new, ML-driven transcript Smart Summary™, we enable analysts to pick up the important information across multiple classifications, such as guidance and KPIs, while skipping over the “great quarter, guys!” parts. The segments based on these classifications can either be seen highlighted in the transcript itself or extracted, with context, in a special field. The text is also run through an NLP screen and color-coded in green or red, if needed, with enabled clickable user ratings that will continue to improve the accuracy of the learning system. In addition, Smart Summary offers keyword extractions, enabling readers to view text related to these surfaced key terms.

These features empower analysts to get the essential information in minutes, saving valuable time during the busiest periods of the year. The benefit of the ML-driven Smart Summaries does not end with faster information processing or expanded coverage; it also ensures that analysts are not missing important information on their last few transcripts at the end of the workday. 

Below we are looking at Facebook’s latest quarterly call transcript, and scrolling down to the Guidance classification text:

Below we are looking at the same Facebook transcript, but reviewing the Whatsapp key term text:

Another aspect of Smart Summary is “Table View,” which enables active sorting of sentences by the Classification score (ie. “which sentences have the most guidance language?”). This adds another layer of improved accuracy and productivity to the analyst workflow. 

The Table View is also available for surfaced keywords. Analysts can see useful statistics, like whether a keyword is new, or whether it got dropped. They can also see whether usage, by either management or analysts, is going up or down. This type of quantitative insight for keywords was previously so labor-intensive that it was rarely done, and only for one or two key terms at most.

 

How did we build Smart Summary™?

We spent countless hours training a machine learning model on a very large number of transcripts across all industries, effectively automating what an analyst would do. Once the model was up and running, we spent a lot of time on corrections and fine-tuning for this official release. 

Smart Summary™ is a blockbuster new addition to the Sentieo platform that serves our overarching mission: augmenting human decision-making through the latest technological tools. The release is a part of the latest ML/NLP update to our industry-leading Document Search, which now also includes the surfacing of synonym suggestions based on a machine learning tool trained on millions of corporate documents. (We will discuss this in an upcoming blog post).

 

To see how Sentieo’s complete workflow solution can work for you, please get in touch

New call-to-action