The story of Erica, Bank of America’s homegrown digital assistant

Banking digital assistants may be common now, but in 2017, Bank of America was one of the first to be thinking about how they make the firm’s customer experience more powerful. The answer was an in-house build of a digital assistant that required the firm to hire PhDs in linguistics and build a collaboration structure that could facilitate teams from different departments. 

In 2024, BofA clients interacted with Erica 676 million times bringing its total interactions since its launch in 2018 to 2.5 billion. 

On the show today, Hari Gopalkrishnan, who leads Bank of America’s Consumer, Business & Wealth Management Technology team, joins us to tell the tale of  how the firm built its industry-leading digital assistant, Erica.

Hari shares how the firm has gradually expanded Erica’s remit beyond consumer banking to also include multiple lines of business and individual and corporate clients across the firm’s global footprint.

It’s a dive into what it takes to push the boundaries in this industry, how the firm thought about development, testing, expansion, and how Erica’s capabilities can be expanded with the recent innovations of Gen AI. 

Listen to full episode

Subscribe: Apple Podcasts | SoundCloud | Spotify

Source: Bank of America

CX as the impetus behind Bank of America’s investment into building Erica

Back in 2017, Hari Gopalkrishnan’s team realized that despite the expanding remit of the BofA app, customers were still flocking to traditional channels like banks and call centers before they tried self-serving. A dissection of this behavior served as the catalyst for the Erica build. 

“We were putting tons and tons of features into our app, a five inch screen, and our customers were still walking into the branch, calling into the call center … It’s hunting and pecking, and it was hard to navigate once you put more than 10 or 15 key features. And so our first insight was, you want to be able to have your customers interact with a platform in a way they choose, not the way you choose,” said Hari.

Why Bank of America decided on a DIY approach to build Erica

Although the industry is pretty well-versed in building, deploying, and improving chatbots now, the landscape was quite different in 2017, when BofA had first thought of developing Erica. There was no blueprint for what a banking digital assistant looked like and technology providers were few and far between. The slim pickings in the marketplace, as well as the limited applicability most software had in the financial services, fueled an internal build. 

“There were a bunch of startups that were coming out, we spent a few weeks with them and either they disappeared or were going to get gobbled up. So it was a very volatile marketplace for acquiring software that did this. People were trying to play in this game, but weren’t quite getting it. The ones that understood some level of NLU (Natural Language Understanding) didn’t understand financial ontology,” he said.

“We did an assessment, and we looked at third parties, like we always do, but at the end of the day, it just wasn’t going to work out. At the same time, we found a couple of really good open source NLP engines. They were strong, solid, and very well regarded in the industry. We actually hired up a team. We always had good technical engineers. But we also actually hired people with PhDs in linguistics to work on this. Then we started to work with our teams to figure out: what is the digital experience going to look like?”.

How Bank of America structured teams across the org to build Erica

Building Erica required BofA to think across organizational silos, and really invest into creating a collaboration framework that would allow Erica to improve CX without compromising on risk tolerance. 

“We actually took the Agile construct to the next level. We had teams set up in [different] regions which were actually in the room. It was the engineering team, the UX team, the appropriate legal team, all opining day in, day out, on all aspects of the platform. The sprints were not just engineers running off and UX coming in weeks later. It had UX teams embedded. In fact, when I used to visit the teams, it was sometimes hard to tell who was in the design team and who was in the engineering team. That was actually the power of how this came together,” Hari shared. 

The fork in the road: User testing proved presumptions wrong

Designers and developers have a conceptual map of the software they are building and they also spend time trying to understand their users’ behaviors and pain points. But there is no silver bullet for getting everything right, right off the bat. Hari shares how testing motivated a major pivot in Erica before it launched. 

 “We thought we would have to invest just as much in voice as in text -– that people would half the time talk into the app, and half the time they would type into the app. Then we go to a small group of customers, and we get more feedback from this. And the feedback we got there was people were just typing in text 90% of the time. They were rarely using voice.”

Gen AI potentialities for Erica

Bank of America is not sleeping on Gen AI – it’s just chosen to stay quieter than most. “As we look at the emergence of Generative AI, we actually see that classification can actually get a lot better. You can actually talk even more naturally in a natural language. So that is just a natural sort of expansion of where we go with Erica. We have about 25 different proof of concepts right now, many of them are actually about to get into production, which use a Large Language Model in some way, shape or form, to continue to enhance the work that we’ve been doing,”. 

The following excerpts were edited for clarity

BofA’s blueprint for Erica’s expansion into multiple lines of business

Some of it actually is using fit for purpose language models that are pre-trained on certain things. So, for example, for employees there are available technologies that actually are trained on things like integration into your HR system and integrating into your help desk system. We don’t want to go build a whole bunch of things that actually have been built by somebody before. 

The reason we built what we built is because nobody was building that before. When it came to employees, we realized that we can leverage all the goodness we have on NLU (Natural Language Understanding) and User Experience. We also found that there are available models that actually do a really good job of NLU to service intent and to calling of existing HR platforms. 

We had to figure out case by case, do we start a native build? Do we integrate with existing models when it comes to Erica for business banking there? We had to go to a different set of data sources. You had to make sure those sources were clean. You had to make sure, in some cases, that there was an API available to make that interaction happen … in some cases, many of the services in the past may have been built for a specific User Experience or a specific application, we had to make sure that they get rebuilt or reimagined to be invoked by a chat bot, because sometimes you may need clarifying steps. You may have a multi-step process before you actually call an interaction. That also helped us become better in our core platforms, because that helps us now be ready for the future. 

How BofA is balancing ROI, risk, and innovation when it comes to Gen AI

We have an AI Council. Even though we’re obviously a very large company, we try to work in a very integrated fashion and look to learn from everything that’s going on across the company. There are lots of parts of this company, and we come together. You could say it slows us down, but we’re okay with that. We ask, what are the pilots and POCs you want to run? And why do we want to run those POCs and pilots? The people involved in that council involve senior business leaders, senior strategy leaders, senior risk leaders. We’re asking, does this thing align with our risk framework? We have a risk framework that has 16 points of risk. You can imagine bias, intellectual property, transparency, and explainability, in there.  

Is the work you’re going to do, going to abide by those risk frameworks? Is there an adequate human in the loop so that you can make sure that the thing doesn’t run away? How do you measure the performance? What guardrails are you going to implement? Those are the things we look at as we implement any of these proof of concepts and eventually take them to commercial use. 

The second part is we also look at, what is the mindset you have on the ROI generation of doing this work, because none of this stuff is cheap. This is something everybody is wrestling with. There’s so much hype out there that people are throwing out, I’m going to spend a billion dollars. I’m going to spend $5 billion and when you ask the question, tell me what your bottom line is going to be, what are you going to get in return? The answers are a little bit more diffused. 

So we’re taking an approach of saying, we want to understand how work gets done. We want to understand activities, jobs, tasks. We want to understand what part of those tasks cost, what money. And then, when you implement solutions like this, what’s the ROI? 

Sell your investment strategies (without the cost and burden of creating a fund)

screener

I frequently meet people with really compelling investment strategies and ideas.

Hey, can you help me raise some money?

They’re looking for help putting together a fund to demonstrate exactly how good their strategy or stock picking really is.

Starting a fund is hard…and expensive

It’s not that I can’t really help them — it’s that starting a hedge fund or mutual fund is pretty complicated and expensive. You need to see significant growth in assets to be able to scale these things to profitability (once they achieve that, though, they’re pretty damn profitable).

Like any startup, the chances of these startup funds achieving escape velocity — getting enough traction to turn their good ideas into profitable ones  — is pretty slim.

But, there are other ways of putting your investing talent to work and make money while doing it — all without the headache and onerous infrastructure needed to manage a fund or a regulated investment advisory.

How to make money from your investment ideas (without starting a fund or having $$)

Here are 5 ways to get started selling your portfolio strategies:

Continue reading “Sell your investment strategies (without the cost and burden of creating a fund)”

Winning strategies: Investing using policy as a guide – with James Juliano

policy based investing

A lot of investors claim they’re focused on the big picture.

Others give lip service to their focus on “the long term”.

James Juliano, partner and portfolio manager at Kairos Capital Advisors, walks the walk. He and founder of the firm, Russell Redenbaugh, use economic and government policy as a guide for their investment decisions.

James joins us on Tradestreaming Radio to talk about how he deciphers the policy tea leaves and how those big ideas get implemented tactically int their portfolio.

Listen to the FULL episode


Continue reading “Winning strategies: Investing using policy as a guide – with James Juliano”

Using Google to forecast a stock’s reaction to earnings reports – with Darren Roulstone

Smart investors are looking at various data sets to help give them an edge with their investing. Some of this information is financial in nature — much of it isn’t.

Professor Darren Roulstone has studied how investors are using Google to search out financial information and what search volume may say about future stock prices.

Continue reading “Using Google to forecast a stock’s reaction to earnings reports – with Darren Roulstone”

Using Google to forecast an earnings pop (or plunk)

Google’s my friend.

Not only do I rely upon it for email, video, and of course, search, but I’m using it to invest  better and smarter (the Tradestreaming way, right?).

Let me explain:

One of my first podcasts on Tradestreaming Radio was with finance professor, Joey Engelberg. In How to use Google search data to invest, I asked Engelberg about a paper he had recently published that showed how useful Google could be in forecasting stock prices.

Using Google Search Data to Invest by tradestreaming

Specifically, Engelberg noticed:

  1. Google search volume likely measures the attention of retail investors
  2. and does so in a more timely fashion that existing proxies of investor attention

And of course, stock prices tend to follow attention.

So, an increase in Google search frequency (SVI) predicts higher prices in the next two weeks and also contributes to a large first-day return (and long-run underperformance) of IPO stocks.

Awesome stuff and after we spoke, Joey kind of went underground (he did leave UNC and headed for UCSD), using his research to make coin at a hedge fund. I spent a whole chapter in Tradestreaming (my book) describing co-lateral research — stuff that’s inherently non-financial in nature (Google search, Amazon ratings, etc) to help us make better investing choices.

Now a new paper shines light on how Google search reflects investor information demand and what that means for earnings news.

Continue reading “Using Google to forecast an earnings pop (or plunk)”

Two new ways to invest with an insider trading strategy

Direxion Shares, the fund group known primarily for its leveraged ETFs, is moving into more buy-and-hold strategies.

And the firm is doing it first by launching 2 ETFs that use variants on Sabrient’s Insider Sentiment Index.  Direxion announced that it was floating 2 funds:

  • Direxion Large Cap Insider Sentiment Shares (NYSEArca: INSD)
  • Direxion All Cap Insider Sentiment (NYSEArca: KNOW)

You can see the prospectus for both funds here.
These two funds join Guggenheim’s Insider ETF ($NFO) — also powered by Sabrient’s Insider Sentiment Index.

Continue reading “Two new ways to invest with an insider trading strategy”

[Free Webinar]: From the ground up: Building a better money management business

This event was already held. Check out this event’s presentation, Building an investment advisory business from the ground up.

From the ground up: How to build a successful money management firm

Join us for a Webinar on May 16
Space is limited.
Reserve your Webinar seat now at:
https://www3.gotomeeting.com/register/545041518
Is your investment practice what you want it to be? 

Many professional investors have changed their business models over the past few years.  Wirehouse brokers are breaking out and going independent. Many are choosing to start or join existing RIAs.  Many others are creating their own hedge funds.

Everyone is looking for the right business model, the right structure for their investment business.

Cale Smith, founder of Islamorada Investment Management, believes he’s built a better investment business mousetrap.

Called Spoke Funds®, these structures solve some of the problems associated with mutual funds (underperformance, tax inefficiency) and hedge funds (compensation schemes masquerading as an asset class).

The Spoke Fund® structure aligns incentives by ensuring the investment manager invests most of his liquid net worth in the same portfolio he’s selling to investors.

In this webinar, you’ll learn:

  • why the existing vehicles for your business (mutual/hedge funds) are broken
  • How Spoke Funds solve these problems
  • Why Spoke Funds are perfect for managers who are value investors
  • How they lower start-up costs and get into business faster
  • How their transparency is attracting a new class of investor

Please join Zack Miller of Tradestreaming.com and Cale Smith of Islamorada Investment Management for a frank and open chat about the future of the investment management business.

Title: From the ground up: How to build a successful money management firm
Date: Monday, May 16, 2011
Time: 4:00 PM – 5:00 PM EDT
After registering you will receive a confirmation email containing information about joining the Webinar.
System Requirements
PC-based attendees
Required: Windows® 7, Vista, XP or 2003 Server
Macintosh®-based attendees
Required: Mac OS® X 10.4.11 (Tiger®) or newer

 

Hedge funds beefing up after good returns, inflows in 2010

The hedge fund industry certainly took a drubbing in the bleak market years which were 2007 – 2008.  But, they’re back and they’re back on the heels of good performance and inflows in 2010.  Credit Suisse released its 2010 Hedge Fund Industry Review (.pdf)  today.

Few highlights:

  • Hedge funds, as measured by the Dow Jones Credit Suisse Hedge Fund Index, were up 10.95% for 2010 after posting positive performance for seven out of 12 months
  • On an asset-weighted basis, an estimated 81% of funds have surpassed previous high water marks as of December 31, 2010
  • The industry saw an estimated USD $8.5 billion in inflows for the fourth quarter, bringing overall inflows to $22.6 billion for the year. This represents the largest annual inflows into the space since 2007
  • The largest inflows in 2010 were seen in the Global Macro and Event Driven Sectors, up $16.8 billion and $13.9 billion respectively, while the largest outflows were seen in the Multi-Strategy sector which lost $16.9 billion
  • Including performance gains, current hedge fund industry assets under management (AUM) grew to $1.7 trillion as of December 31, 2010, up from $1.5 trillion on December 31, 2009
  • Research of returns from January 1996 through December 2010, indicates that smaller hedge funds (less than $100M AUM), have historically outperformed larger hedge funds (greater than $500M AUM) by 3.95% annually

Check out the whole report here.

Tradestream Radio Episode 1

building an investing empire

This week’s Tradestreaming Radio is live.  I discuss

[audio:https://66.228.46.202/wp-content/uploads/2010/11/TradestreamPodcast_November14_1.mp3]

Transcript

Hi, this is Zack Miller, and you’re listening to Tradestreaming Radio. I’m the author of www.newrulesofinvesting.com and the author of the recent book Tradestream Your Way to Profits: Building a Killer Portfolio in the Age of Social Media. And, Tradestreaming Radio is our home in the internet radio space, and we hope to use this forum to expound upon some of our ideas and bring in some interesting people who have ideas of their own that I think you would find quite interesting.

I, myself, am focused on sort of the intersection between online media and investing. And, my book, Tradestream Your Way to Profits, outlines eight strategies that call from my experiences as a business development person at Seeking Alpha, a hedge fund analyst, and now a independent asset advisor.

So we can just jump right into it.

So tradestreaming as a theory, as a philosophy is all about finding the most valuable information from the most valuable person with that information, making that available through social media. One of the strategies that I find most appealing from this vantage point is insider trading, right? So, tradestreaming is finding people who have a strategy that’s been proven to work either academically, or in practice, hopefully the marriage of the two.

Insiders, we’re talking about corporate insiders now, have the ability and have the demonstrated ability to outperform markets over the long-term. And, I devote an entire section of my book, an entire chapter, to an insider trading strategy. It’s a two-tiered strategy, and I wrote about it recently on the blog, check it out there. But, I talked about the Muzea  model, a behavioral model. He was broker-sum-insider trading strategy guy named George Muzea, who wrote a book called The Vital Few vs. the Trivial Many: Invest with the Insiders, Not the Masses. And he attributes outperformance by insiders to a behavioral basis. So, he segments insider trading activity by looking at the behavior of insiders, and trying to get into their heads to better understand the rationale behind their trades.
So therefore if you were going to implement a strategy based upon Muzea you’d want to focus on who is doing the trading, what Muzea calls value insiders, 70% of trades done by insiders with a long-term view of their firm.

He also segments out catalytic insiders. These are corporate types not concerned with book value of their firm, but rather they see, you know, a temporary anomaly in the pricing of their stock and they may step in to buy or sell the stock.

I found that there was another model, the Seyhun model. Nejat Seyhun is a professor of business at the University of Michigan. Wrote a book called Investment Intelligence from Insider Trading. He creates a bit more detailed model where he creates a hierarchy of insiders ranking in order of their access to higher quality tradable information.
So starting at the top you have senior management, C-level executives who have their management finger on the pulse of their firms. Though they’re not allowed to trade on what’s called insider information, which would be, you know, private, or non-public information, that if made public would obviously affect the stock price. Definitely they have a view of their firm. You know, they see sales reports, they know about partnerships they’re working on. And, you know, they know better than anyone else the dynamics of their industry. They are quality players and when they step in and buy or sell their stock, particularly on the buy side, people should take notice.

Then next down you have officers, employees of the firm, not senior enough to make senior decisions, but definitely affect the operating of the company as a whole. You have directors, people who sit on the board of directors but are outside of the firm. They have very little information, right? So, they’re sitting at quarterly board meetings, or something like that. They’re not actually part and parcel of the day in/day out inside of a company. And then you have large share holders, these are hedge fund guys, institutional types who own more than 10% of the stock.

So the strategy here is, and you know, you can read the book for more information, but it’s to focus on active versus passive insider transactions. We want to focus more on the buy side. You know, particularly corporate insiders sell stock for all types of reasons, particularly in technology stocks. There’s options, you know, exercising all the time. And a lot of that is just noise. That’s people getting liquid. It’s diversifying out of their holdings. The research shows that on the buy side when somebody steps in with their own hard-earned money and decides to purchase their own company’s stock it’s a lot more indicative of future price movements.

So, we want to focus on buys, not sells. We want to look at clustering and consensus. Insider trading activity is a much better indicator of future movement in stock price when multiple insiders are buying at the same time, called a clustering, without a conflicting trade, and that’s called consensus. We want to look for three or more insiders stepping in and all participating in buying or selling their stock as an indicator.

This strategy works better looking at small caps. We want to mirror corporate insider buying, so less than a billion dollars is sort of the sweet spot for this strategy. We want to look for earning surprises. It’s a good idea to look for insider buying activity in firms that recently reported a positive earning surprise for some reason. You know, we’ll see insider buying as continued momentum play there. And bigger is better. Larger purchases are better signals than smaller ones. We want to look for purchases over 10,000 shares. Obviously, you know, how big the purchases will also depend upon the price of the stock. So, 10,000 shares in a stock that’s worth $1 is not necessarily a great signal, but in general that’s, we want to see a larger purchase. Obviously we want to see corporate insiders putting more money up to show more conviction.

So in all these methods, all these methods improve returns. The three most important determinants of quality are, to repeat, top executives. We want to see the C-level executives buying. We want to see them buying in small firms, right? The fact that somebody at 3M is buying is a good thing, but not as good as somebody, you know, at a smaller micro cap. And, we want to see a big position. We want to see them stepping up.

So, to quote a research report by Piotroski and Roulstone entitled Do Insider Trades Reflect Superior Knowledge About Future Cash Flow Realizations? They said we find strong evidence that insider trades are associated with the firm’s future earnings performance. Consistent with insider trading on the basis of both security misevaluation and private information about future cash flows. So, you know, obviously to do this it’s going to take some legwork, right? So, you know, I haven’t found a perfect system that mimics the Seyhun model. There are some premium sites that allow you to do such a thing.

You know, you can actually theoretically do this through using the SEC database, or through Yahoo Finance, which is free. A site called J3SG, which is kind of a funny name, but it’s a good site that follows insider activity. They have a free version and a premium version. The premium version actually does a lot of this for you. There’s Guru Focus, which a lot of people use.

A new blog, which I think is really helpful called Insider Monkey, which is following a lot of insider movements and expounding upon some of these theories that I’m talking about. Asif Suria has a site called SINLetter that actually does, you know, a rundown on insider buying and selling.  Finviz is a screener that can be used to screen for some of these types of stocks. Insider Cow and Old School Value insider buy screener, are some of the resources that I put up there. You can find that all on the blog. I would definitely check out that strategy, that’s the insider trading strategy.

So, next up in Tradestreaming Radio for this week I wanted to focus on what we call ‘trend watch’. This is something that I’ve chosen that I think is interesting. I hope you find interesting. Today’s trend has to do with consolidation in sort of the second generator online broker platforms.

Obviously, you know, we have two big players, well, three big players in the online broker space. We’ve got Ameritrade, Etrade, and Schwab. The reason I stumbled upon that is because Schwab, you know, I don’t think is a classic online broker. Obviously they do have online brokerage access.

We’re seeing second generation platforms that emerged more recently begin to consolidate, and the first thing we saw last week is interactive brokers, it’s a platform that a lot of new investment advisors, registered investment advisors, RIAs, are building their portfolios on. They do a lot of this mirroring type thing where you can actually manage your portfolio and bring in managed accounts that are executed automatically when you make a change in the model portfolio.

Interactive Brokers took over a 6% position in trade station. We saw Ameritrade enter this fray with the ThinkOrSwim purchase. I guess that’s probably about 18 or maybe 24 months ago already, and reportedly in the industry that was a great purchase on their behalf $600, $700 million. I don’t remember the exact number.

And, now we’re seeing, you know, consolidation, or perhaps potential consolidation at the second generation brokers who really have built, you know, really powerful technology platforms. That’s what they are first and foremost. And they’re technology platforms that are attracting sort of the next generation investment advisor business. So, I’d keep your eye on that.

Next up on Tradestreaming Radio is our deal watch. Just this week we’ve launched Tradestreaming Marketplace We’re going out and sourcing the best of breed financial/investing products, negotiating on our community’s behalf and offering really valued added deals.

This week is what I like to call value investing in the sports betting marketplace. So, I like to tell the story about famed value investor Joel Greenblatt, who as you know probably as the author of The Little Book That Still Beats the Market. And, he’s the founder of The Magic Formula, which is posted returns of, you know, about 40% a year for 20 years. He explains his results when you ask him. It’s nothing more than a focus on what makes a good investment in the real world. And, he throws in a little sixth grade math to boot. In Greenblatt’s world this strategy extends to schooling. He’s also focused on turning around failing schools in the New York area, and he’s had great success with that.

So the way I think of it is value investing can be applied to an educational model, it can be applied to anything. I’m an investor who uses valued based principles in my investing strategy and tradestreaming, in my book. Everything that  I’ve written about on my blog is about identifying and investing in low-risk/high-pay off targets. And, that’s what got me thinking about sports betting.

I’m not a gambler at heart, for sure not, but I do believe the internet has opened up new markets that weren’t easily accessible before. We’ve seen examples in online Forex, obviously offline Forex is a huge market. It’s extremely easy now to open up an online Forex account and be able to trade currencies. We’ve seen peer to peer lending, the prosper.coms of this world. I wrote about this in my book as well. This has social value for sure, but it’s also an opportunity for enterprising investors.

So, why would somebody bet on sports? There’s liquidity. You have marketplaces now where you can find bid and ask. There is some transparency. You can see sort of the, you know, price movements. You can get your hands on historical data, so you can build strategies that take advantage of this. It’s odds based success. So, just like investing, you know, you don’t have to be perfect 100% of the time, but if you can be more, you know, more than half the time right you can actually make money this way. There’s continuous pricing. And, what a lot of people like about it, and this is sort of the gambling aspect, is the instant gratification.

So, I was drawn to a new book on the market written by Daniel Fabrizio. It’s called Sports Investing: Profiting from Point Spreads. The title was compelling, obviously, because you know all of a sudden, you know, instead of betting it was investing in sports. That’s not quite accurate, but you know, it sort of took it out of the gambling realm and turned it into something that’s more familiar to me.

So, I like this book. It does a few things really well. It differentiates between investing and betting. It uses data to formulate some winning strategies, and a few of the strategies in the book are- one strategy is value, one’s contrarian, one’s momentum based.
There’s details on how these strategies work with each of the major sports, so football, baseball, basketball, hockey. Sorry, no soccer. There’s a section on Monte Carlo analysis to advise how to manage your portfolio and position size, this is sort of the bank roll in sports betting lingo. And it explains how to lower vigorish, which is the equivalent to a spread in a stock. This is where sports books make their money, their commissions.
It’s an introductory book. It’s very short. It’s not made for an advanced sports better, but for me, who’s a neophyte in this whole thing it was a good introduction, and gave me a little bit of meat to be able to go onto the next step.
Fabrizio doesn’t just write books, he actually has a full blown sports betting platform. He’s not a marketplace, but he has a research tool called sportsinsights.com

I took out a subscription there and basically all the theory that is, you know, elucidated in the book comes to life in Sports Insights. And Sports Insights was developed in part by a Quant from MIT. And, you know, in there you can get access to contrarian value strategies. There’s strong historical evidence to show that betting against popular opinion can be profitable, so obviously value investors know that. The same holds true in sports.
There’s a momentum strategy. Some investors like to let the winners run. And, sports investors can find strategies, odds-based strategies, that work in that way.

There’s also a fundamental analysis tool where you can rank a team, you know, based upon whatever is going on, you know, in that team itself, or in an individual player himself. And, just like you have in real life investing there’s special situations. So, you know, Sports Insights allows some betters to zero in on certain intangibles of the game, or the direct correlation of how two teams match up against one another.
It’s not perfect, and Fabrizio is the first to tell you that, and he warns against, in general, using any platform that makes bold and audacious claims.

I feel that having spent some time managing this system, it’s a great system, it’s a great way to get your feet wet in sports betting, particularly if you have the value investing bent. And, the deal is great. I mean, so we went out there, basically you get a $40 book, which is Sports Investing: Profiting from Point Spreads, Fabrizio’s book. You get six month premium access to Sports Insights, which is worth about $600. And, we’re putting together an exclusive webinar for anyone that purchases this package through Tradestreaming.com called The Three Secrets Investors Should Know to Make Money in Point Spreads. It’s going to be led by myself and by Dan, and it should be great.

And, on top of this there really is no risk. So, again, you want to lower your risk whenever you make a purchase, whenever you’re investing in anything. There’s a 30 money-back guarantee. So, you’ve really upped your odds for success. Check it out on the site. We’re selling it for $399. You know, it’s about 40% off retail price. Check it out. Let us know, and join the Tradestreaming revolution. Thank you for listening, and I hope you will join us again next week.

Can you trade on rumors? One possible model

In Tradestream, I spent a whole chapter looking under the covers of investing/trading strategies that focus on rumors.  Greater sentiment analysis (like the hubbub that erupted after Prof. Bollen published a paper on using twitter to predict stock market swings) is in early days but at its core is a desire to use news/chatter to better gauge future stock moves.  Bold and audacious, but not nearly there yet.

Rumors: A Model

In the book, I developed a model upon the one Cass Sunstein (co-author of Nudge and just a prolific writer/thinker) used in his most recent book, On Rumors: How Falsehoods Spread, Why we Believe Them, What Can Be Done.

Rumor transmission often involved the rational processing of information, in a way that leads people quite sensibly in light of their existing knowledge, to believe and spread falsehoods.  This problem is especially acute on the Internet — Cass Sunstein, “She Said What?  He Did That? Believing False Rumors,” Harvard Law School Public Law Working Paper No. 08-56 (November 2008), 2

Sunstein describes a useful framework with which to understand how rumors get started and how they get propagated — influencing decision making.

Sunstein describes the various actors in the social transmission of false information.  While he focuses on rumormongering, I try to apply this framework to investing.

  1. Propagators:
    1. self-interested, varying degrees: they may own a stock and work to discredit those who don’t like it or are short
    2. altruistic: sincerely interested in promoting some type of cause — these guys don’t even realize that they are spreading falsehoods
  2. Priors: success or failure of rumors depends on how closely they approximate the prior beliefs of those who hear them
    1. motivations: people don’t enjoy hearing bad things about ideas/people close to them and conversely, they are more open to receiving false info about something they dislike
    2. beliefs: Sunstein says that people who have strong prior beliefs usually do so because of what they know and therefore, require a lot of supporting information to upseat those beliefs
  3. Cascades: the mechanisms of rumor transmission, why/how/when people accept/reject a rumor is intimately connected to how the information affects their personal desires
    1. informational: groups of investors are led to accept a thesis in spite of individuals’ private info.  Think of all the hating that goes on on Yahoo Message Boards.
    2. reputational: people can be led to believe things in conflict with their priors but do so to curry favor with others.  This is equivalent to a fund manager on CNBC pumping his portfolio — as an expert — his status and street cred influence others’ beliefs (whether correct or not)

So, we have to narrow our focus down to why stocks move they way they do when unsubstantiated news — rumors — are floated.

Rumors and Preannouncement Trading

I chose to focus on rumors surrounding M&A announcements.  Many times, the Wall Street Journal will publish stories on unsubstantiated mergers and acquisitions.  Target stocks will jump and acquirer stocks drop.  That said, though, many of these rumored M&As fail to consummate.

“While sellers lose money when a rumor precedes an actual announcement, in most cases rumors fail to materialize into public announcements.” Rumors and Pre-Announcement Trading: Why Sell Target Stocks Before Acquisition Announcements?” (Gao, Oler)

Given the research of Gao and Oler:

On average, stock prices of rumored firms drift down to their pre-rumor level over a 70-day period after the initial price jump when a rumor is published and that only 12% of rumored takeovers materialize into actual announcements within 70 days.

So, really, Tradestreaming would be all about finding the right side of this strategy — where the numbers, data and probability is with the investor.  That would mean taking the other side of the trade.

The Antitakeover Strategy

  1. Research WSJ for reported but unsubstantiated M&A
  2. Remove all mega cap firms (<$20B)
  3. Short a basket of rumored acquisition targets and hold 70 days after the rumor first appeared.  You can hedge by going long the market if you like.
  4. Strategy performs even better during periods of increased M&A activity

Performance

The researchers found that this strategy would put up 4.2% in abnormal returns — when you further restrict the strategy to hot M&A years, profits go up to 12.7%.