The crossword puzzle of fitting - why across and then down?

This will be the first in a series of posts about portfolio optimisation. Main reason being I'm planning to write a book about backtesting, and that will include a big chunk of material on optimisation. Yes, I know, my latest book isn't out yet (it's out in December - in time for Christmas). But this backtesting book is going to be quite deep (and probably long!) so I need to start researching now if it's going to be written any time soon. Today's post is not that deep, and is quite short. It has literally been written whilst waiting for the rather extensive testing of the second post to finish. Anyone, let's begin. 

One of the issues when fitting is to decide how to structure and order the process. In very abstract terms, a component of a trading strategy will consist of a forecast to predict the price of an instrument. A forecast might be something like momentum16,64 - that's the exponentially weighted moving average crossover with spans of 16 and 64 days to you my good sir or madam. An instrument is something like the US 10 year bond future. We can represent all these options in a grid like so:

             momentum16,64                momentum4,16                 carry10

US10             X                            X                           X

SP500            X                            X                           X       

US5              X                            X                           X      

.... where each 'X' is a place on the grid. If those were white squares, and if you can imagine that if there were some forecasts missing from certain instruments which were black squares, then we'd have a crossword grid. Yes that's all I've got. Quite a weak link. Apologies.You think it's easy coming up with catchy blog titles?

And note that this is a tiny subset of the full grid. Instead of these 9 possibilities my full trading system currently has 10,373 options. That's 40 trading rules across 260 different instruments. Some of those instruments are duplicated (eg SP500 mini and micro), some are no longer traded; but that still leaves 204 instruments and over 8,100 options.

Anyone it should be obvious that in doing our fitting we have a few options:

• A joint fit where we fit everything in one go. 8,100 options. In one go. Let that sink in.
• A natural clustering where we cluster together things that are correlated.
• A down and then across structured clustering where we first fit within rules - so for example working out what the best blend of US10, SP500 and US5 is within the carry10 rule - and then across rules - so estimating the best blend of carry10, momentum16,64 and momentum4,16.
• An across and then down  structured clustering where we first fit within instruments - so for example working out what the best blend of carry10, momentum16,64 and momentum4,16 is within US10 - and then across instruments - so estimating the best blend of US10, SP500 and US5.

Now I've generally done the final one of these four options: across and down. And it's quite a natural way of doing things; because we seperate out the idea of predicting the price of a given instrument, and then put together a portfolio of trading substrategies one per instrument. But I've never actually tested the assumption that this is the right thing to do. In particular, if we were to do a natural clustering, would it come out quite like across and down; or would it be something weird? Or would, for example, all the momentum rules be more correlated with other irrespective of instrument, in which case down and across would make more sense?

Programming note: I've done this type of clustering before; here for underlying instrument returns, and here for forecasts. 

TLDR: There is no evidence to suggest that changing my fitting approach is desirable, but there are some pretty pictures to look at!

Before I begin, I did decide to limit the analysis to the last 10 years. It's kind of slow just calculating a correlation matrix from 52 years of data and many instruments dont't have data except for the last 10 years anyway. I also resampled the returns to a weekly frequency. This is what I do when optimising anyway. Unless your returns are very quick, this won't affect correlations much. That leaves us with 520 weeks (I know that isn't exactly 10 years. Let me check to see if I give a toss. No, I don't) or rows in a dataframe, with over 8,100 columns remember. That's about the limit as to what my laptop can calculate a correlation for; and it's quite a painful process to cluster these bad boys as well.

Anyway let's begin. I've come up with quite a fun way to visualise these clusters which you can see here for the first two cluster plot:

OK as you can see each cluster has a subplot. Each splot has two stacked bars. The lefthand side shows the composition by asset class. The righthand side shows the composition by trading rule. You can just about make out from the legend what the various colours mean. Note these aren't portfolio weights, and just reflect the number of instrument/rule combos in each category. 

If your eyes are very good you will see the tops of the left hand bars don't quite reach 1. This is because I've removed anything with less than 2% of the total from the plots for clarity. Mainly this is a few odd instruments in a few very small asset classes (like volatility). It doesn't affect trading rules, since even the mrinasset rule has 1/40 = 2.5% of the total count.

The important thing here is we aren't yet seeing any evidence of clustering eithier by instrument or by trading rule. If we were, there would be a preponderance of colours on one side or the other. For example, if correlations were higher amoungst trading rules even from different instruments, then one cluster would have a lot of blue and purple in the right hand bar of one cluster (colours I assign to more divergent rules like momentum), and yellow and orange in the other right hand bar (colours that are reserved for convergent rules).

At this stage then there is no evidence that rows or columns makes more sense. 

Here is the three cluster plot. All three clusters look very similar for both instruments and rules, again suggesting there isn't much going on here yet on eithier axis.

I'm going to skip through the next few plots, since none of them show anything interesting. Let's check in at N=16:

Still not much going on here! We aren't seeing clumps of colours developing for eithier bar.

N=36:

49:

Never have so many coloured pixels mean wasted for so little result!

Let's close out with N=64, a nice power of 2 to finish on, as we're reaching the point where the plots are getting so small they're impossible to see:

There you have it folks. No clear evidence for eithier across-> down, or for down-> across. 

Now, there are a few alternative conclusions we could draw here. One is that there is some weird deep correlation pattern that the simple analysis by asset class and trading rule doesn't pick up. I don't buy that. If for example we look at the final cluster from N=64, it looks like this:

[assettrend4 forecasting AEX, breakout80 forecasting AEX, momentum32 forecasting ALUMINIUM, breakout160 forecasting AUD_micro, assettrend16 forecasting BITCOIN, normmom64 forecasting BITCOIN, accel64 forecasting BONO, carry125 forecasting BOVESPA, momentum64 forecasting BOVESPA, breakout80 forecasting BRE, normmom4 forecasting BRENT_W, accel32 forecasting BTP, momentum8 forecasting BTP3, accel16 forecasting BUTTER, assettrend16 forecasting BUTTER, carry125 forecasting CAD, assettrend32 forecasting CAD10, relcarry forecasting CAD2, breakout20 forecasting COAL, breakout40 forecasting COPPER_LME, relmomentum40 forecasting COPPER_LME, relmomentum20 forecasting COTTON, breakout320 forecasting DOW, assettrend8 forecasting EU-AUTO, relmomentum40 forecasting EU-CHEM, assettrend2 forecasting EU-CHEM, normmom2 forecasting EU-CHEM, relmomentum80 forecasting EU-DIV30, relmomentum10 forecasting EU-DJ-TELECOM, relmomentum20 forecasting EU-HOUSE, relmomentum20 forecasting EU-INSURE, carry10 forecasting EU-MEDIA, accel32 forecasting EU-OIL, assettrend2 forecasting EU-TECH, carry10 forecasting EU-TECH, breakout20 forecasting EURAUD, momentum8 forecasting EURCAD, carry30 forecasting EURCHF, carry60 forecasting EURCHF, normmom8 forecasting EURIBOR-ICE, mrinasset1000 forecasting EUROSTX, momentum4 forecasting EUROSTX-SMALL, normmom16 forecasting EUR_micro, assettrend32 forecasting FANG, mrinasset1000 forecasting FED, assettrend4 forecasting FED, normmom32 forecasting FEEDCOW, carry60 forecasting FEEDCOW, accel16 forecasting FTSECHINAH, breakout20 forecasting FTSEINDO, relmomentum20 forecasting FTSEINDO, breakout10 forecasting FTSETAIWAN, normmom8 forecasting FTSEVIET, breakout80 forecasting FTSEVIET, breakout40 forecasting GASOIL, relmomentum10 forecasting GAS_US_mini, momentum8 forecasting GAS_US_mini, mrinasset1000 forecasting GICS, accel32 forecasting HANGENT_mini, skewabs365 forecasting HANGENT_mini, carry30 forecasting HOUSE-US, momentum8 forecasting HOUSE-US, breakout320 forecasting HOUSE-US, assettrend2 forecasting IBEX_mini, relmomentum20 forecasting INR, normmom2 forecasting INR, normmom64 forecasting IRON, accel64 forecasting JGB, carry10 forecasting JGB-SGX-mini, normmom16 forecasting JGB-SGX-mini, assettrend4 forecasting KOSPI_mini, mrinasset1000 forecasting KR10, normmom32 forecasting KR3, momentum4 forecasting KR3, relmomentum40 forecasting KRWUSD_mini, normmom64 forecasting LEAD_LME, carry125 forecasting LEAD_LME, breakout10 forecasting LEANHOG, relmomentum40 forecasting LIVECOW, relcarry forecasting LIVECOW, breakout160 forecasting MILKWET, assettrend2 forecasting MSCIEAFA, skewabs180 forecasting MSCIEMASIA, relmomentum20 forecasting MSCIEMASIA, skewrv365 forecasting MSCIEMASIA, breakout160 forecasting MUMMY, normmom16 forecasting OAT, breakout80 forecasting OJ, skewrv180 forecasting PALLAD, normmom2 forecasting PALLAD, normmom64 forecasting PLAT, normmom16 forecasting RUSSELL, normmom2 forecasting SEK, skewrv365 forecasting SHATZ, normmom64 forecasting SHATZ, accel16 forecasting SHATZ, carry30 forecasting SHATZ, breakout10 forecasting SILVER, assettrend8 forecasting SMI, breakout40 forecasting SMI-MID, momentum16 forecasting SMI-MID, momentum64 forecasting SOFR, carry30 forecasting SOYBEAN_mini, normmom2 forecasting SOYBEAN_mini, skewabs365 forecasting SOYBEAN_mini, skewrv365 forecasting SP500_micro, skewabs365 forecasting STEEL, skewrv365 forecasting SUGAR16, relmomentum80 forecasting TIN_LME, carry10 forecasting TIN_LME, relmomentum40 forecasting TWD, normmom8 forecasting US-ENERGY, carry30 forecasting US-MATERIAL, mrinasset1000 forecasting US10U, carry10 forecasting US2, momentum32 forecasting US30, breakout40 forecasting US30, relcarry forecasting US30, skewrv180 forecasting US5, momentum64 forecasting V2X, carry125 forecasting VIX_mini, breakout10 forecasting VIX_mini, skewabs180 forecasting VNKI, normmom4 forecasting WHEAT, relmomentum10 forecasting YENEUR, assettrend4 forecasting ZAR, accel64 forecasting ZAR]

I look forward to anyone who can give me a coherent story as to why those things are lumped together. 

Personally I'm taking the absence of any contradictory evidence as evidence that I should continue to do what I've done before: fit across and down. Doing some kind of all group clustering or all in one fit, or doing down and then across; none of these seem to offer clear advantages. So why not stick with a simple thing that works?

Note - there is no reason why in theory you could not do an 'all in one' fit or weird clustering, and still use the procedure of generating a combined forecast for an instrument, then a subsystem position for an instrument, and then forming a portfolio. You just take the weights for each rule/instrument pairing from your all in one or weird cluster fit, and then take them across each instrument for forecast weights, and then add up the weights for a given instrument to find instrument weights.

Arguably this has been a waste of time, but the good news is I can recycle this code to visualise forecast weights across a strategy so that's something....

Annual performance update- year 12

 This is how I started last years update: "Mad out there isn't it? Tarrifs on/off/on/partially off/on... USD/SP500/Gold/US10/Bitcoin all yoyoing like crazy."

Well the orange peril is still at it, and as I write this the global supply of oil has been severly curtailed for several weeks now; with a certain amount of reaction in oil futures (which some of it perhaps supressed since apparently "cash on the nail" prices for physical oil are much higher in some delivery ports), but net-net almost none in US stocks. 

As always I do these updates on the basis of the UK tax year, 6th April to 5th April; and as I did last year I'm going to focus almost entirely on my futures trading.

Overall figures 

My total portfolio performance was 6.4%. Almost all of that is down to futures; without it I would have earned just 0.2%. This is not surprise since my long only portfolio has been very low risk, consisting almost entirely of short term bond futures, after I went 100% cash during the taper tantrum (yes, bad move in retrospect, and another failure of discretionary trading on my part). I did start to selectively buy back into equities in the last month or so. Whilst 6.4% is better than nothing, and better than last year, it pales when compared to my Vanguard 80:20 benchmark which was up 23.7% during the tax year. My plan is to refill my equities portfolio over the next couple of years, hopefully using the short term panics which are helpfully generated by the White House every few weeks.

Everything else in this post just relates to futures.

Futures: Headline numbers

Last year in brackets

MTM:        21.9%   (-17.8%)

Interest:    2.7%   (2.4%)

Fees:       -0.04%  (-0.05%)

Commissions:-0.33%  (-0.29%)

Slippage:   -0.55%  (-0.56%)

Net :       23.7%   (-16.3%)

Well first let's note that it is a positive number, and it's also my best performance since 2022 (when another significant conflict started, and I made 27%). Curiosly this is identical to the 80:20 benchmark, at least to one decimal place, but of course that is a silly comparision and a better benchmark is coming later. 

'Interest' includes dividends on 'cash like' short bond ETFs I hold to make a slightly more efficient use of my cash. MTM - mark to market - also includes gains or losses on FX positions held to meet margin, and on the cash like ETFs. MTM breakdown:

Pure futures:    21.7%

Cash like ETFs:  -0.77%

FX:               1.1%

As I did last year then, let's lump together all the interest, FX and ETF MTM and interest, and call those 'cost/benefit of margin':

Futures MTM: 21.7%   (-14.5%)

Fees:        -0.04%  (-0.05%)

Commissions: -0.33%  (-0.29%)

Slippage:    -0.55%  (-0.56%)

SUBTOTAL - PURE FUTURES: 20.7% (-15.3%)

Cost of margin: 2.9% (-1.0%)

Net :       23.7%  (-16.3%)

Time series

You can see that about half the profits were made quite slowly from June to November; and then the other half made very quickly in December and January (we will return to that later). After that things got quite volatile with the whole war thing happening, and risk is currently quite low.

And for the longer term you can see we are pretty much at the HWM set in April 2024, although I never quite got there:

(Note as for all my plots these are non compounded account curves)

Benchmarks

My two traditional benchmarks are the SG CTA index, and an AHL fund which like me is denominated in GBP. A big thanks to Neils from TTU for sharing his SG data as my previous free source stopped working (SG if you are reading this, come on guys, please share!).

First meaningless raw performance:

                AHL       SG           ROB

Mean       5.6%      4.9%         13.8%

Stdev     10.7%      9.0%         17.3%

SR (rf=0)  0.52      0.54          0.80        

Those Sharpes would be lower, especially in the last couple of years, if a risk free rate was deducted.

My correlation is 0.68 with SG CTA, and 0.56 with AHL. Their joint correlation is 0.79.

Now for vol adjusted:

          AHL   SG     Me

30/03/15 68.4% 51.2% 59.5%

30/03/16 -6.4% -3.7% 28.1%

30/03/17 -3.8% -12.6% 2.4%

30/03/18 9.0% -1.7% 2.0%

30/03/19 5.4% -2.7% 4.5%

30/03/20 22.6% 6.5% 33.8%

30/03/21 0.9% 11.9% -1.7%

30/03/22 -12.4% 33.1% 25.8%

30/03/23 8.3% 0.6% -7.6%

30/03/24 14.9% 24.3% 20.6%

30/04/25 -18.7% -18.0% -15.4%

30/04/26 30.3%  29.9%   25.9%

Note: The reason I'm showing 25.9% here and 23.7% earlier, is that these figures are to the end of the relevant month (i.e. March 31st to March 31st), rather than the UK tax year; as I can only get monthly figures for the AHL fund. I've highlighted in green the best performer in each year, red is the worst. 

I've highlighted in green the best performer in each year, red is the worst. A great performance from AHL; their fund was up 18.1% before vol adjustment and as they run at significantly less vol than me this was fantastic. SG CTA also did very well, with raw performance of 15.3%. As a result I was actually the worse of the three for this year at least. 

The CAGR based on monthly vol adjusted figures are 7.7% (AHL), 8.2% (SG) and 13.0% for me.

Market by market

Here is the asset class story:

==================
P&L by asset class
==================

    codes  pandl
    Bond  -2.84
     Vol   0.00
  Sector   0.39
  OilGas   2.21
      FX   2.24
     Ags   3.89
  Metals   5.49
  Equity   5.49

Market wise, the rogues gallery were CAD10 year bonds, plus a few equity markets (SPI200, DOW, DAX) and the US dollar index. I lost between 1% and 1.2% in each of those. The markets where I made more than 1% are quire varied:

          TOPIX    1.0
           PLAT    1.0
            AEX    1.0
        BITCOIN    1.1
            JPY    1.2
       MSCIEAFA    1.7
         YENEUR    2.0
     BRENT-LAST    2.3
            MIB    2.7
     MSCITAIWAN    3.6
        FEEDCOW    4.0
         SILVER    4.2

Silver in particular was quite famous earlier in the year and shows a classic TF curve (price, position, p&l):

Rather overlooked by the legacy media; Feeder Cattle was one of the nicest runs:

Trading rules

Last year almost none of my trading rules made money, all of which contributed to my worst ever year trading futures with my first double digit loss. 

Overall then a much nicer picture for the divergent rules, with convergent less nice except for skew. The best performing model this year at least was the most traditional, the 'momentum' model which is a bunch of moving average crossovers. This probably explains my relative underperformance this year. Also worth nothing that the slowest trend models did the best in almost all categories.

Costs and slippage

My total slippage (diff between mid market price when I come to place an order, and where I get filled) was 0.55% of my starting capital; and commissions were 0.33%. That's an all in cost of 0.88%, very much in line with last year and previous years. Since I switched to dynamic optimisation, my costs have been extremely consistent.

Without my execution algo, if I had just traded at the market, I would have paid 1.34% in slippage; my simple algo earned 78bp and cut my slippage bill by around 40%. 

Coming up

As I noted above I plan to rebuild my long only portfolio out of the smoking ruins of my cash pile over the next couple of years. I also have some interesting things planned in the research and production space this year; you can find more details here.

"Ben Jarvis", the mysterious London Book Club scam, and one of the weirdest evenings of my life

Not a finance post today, but something I feel compelled to write about after one of the strangest experiences of my life. It's also a scam warning, and it's good to share those. So pull up a chair, put your python IDE and copy of Advanced Futures Trading Strategies down, and relax whilst I tell you a story.

A few weeks ago I was sent the following email:

Hi Robert,

I’m the organizer of Classics Book Club London, ages 20 to 45, a community of over 1,000 active readers who are drawn to rigorous nonfiction that explores finance, risk management, disciplined thinking, and practical skill-building. Leveraged Trading stood out to me as a strong fit for the kind of analytical and strategy-focused discussions my members value.

I’m interested in featuring Leveraged Trading at an upcoming Classics Book Club London event. I usually host meetups near a pub by London Bridge, with occasional events in Chelsea. Participation is completely free, and any drinks or snacks at the venue are entirely optional.

Author attendance is completely optional. If attending is not convenient, I can send three short questions by email instead. Your responses would be shared with members during the meetup, allowing readers to engage more deeply with your approach to disciplined system design, risk control, and responsible use of leverage without requiring you to be there live.

Would you be open to having Leveraged Trading featured at an upcoming Classics Book Club London event?

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

This was a little unusual but not totally. I have done talks in rooms above pubs before, although I have never been invited to a book club so I was intrigued. It was also very obvious the email had been written eithier by, or with the help of AI, but I am trying to be less 'judgy' as the kids say so I let it pass. Plus, it's an excuse to go to a pub.

I did a quick google and sure enough they exist:

https://www.meetup.com/classics-book-club-london-ages-20-40/

So I replied:

Oh hi.

That sounds cool. I would like to attend (though I am six years outside your age range!) depending on date and time?

Rob

Hi Robert,

That’s absolutely no issue at all, we'd be delighted to have you join us. The age range is simply a general guide for our core membership, but we always welcome authors themselves, regardless of age.

We’re currently proposing Tuesday, 17 March · 7:00 PM to 10:00 PM GMT, hosted at The Thirsty Bear (62 Stamford Street, London, SE1 9LX). Please let me know if this works for you, and we can confirm everything formally.

In preparation for featuring Leveraged Trading, we would also love to hear more about your journey with the book. Specifically, what initially inspired you to write Leveraged Trading, and at what point did you feel it truly needed to exist?

We’re particularly interested in which of the themes, risk philosophies, or mental frameworks within the book you believe are most urgent or relevant for readers to reflect on today, especially in a fast-moving, high-pressure financial world where decisions are often made under significant emotional and economic strain.

Finally, we would value your thoughts on what you ultimately hope stays with readers after they finish Leveraged Trading  whether that’s a shift in how they assess risk, make financial decisions, approach ambition, or manage discipline and mindset in uncertain markets.

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

Yes, the AI is strong in this one. And he almost certainly hasn't read the book. Never mind, I have been on plenty of 'professional podcasts' where that is also the case.

Hi Ben,

Unfortunately the 17th March doesn't work for me

It looks like from your page you meet on Tuesdays, about once a month? I can do 24th March, 31st March, 7, 14, 21, April, 5,12,19,26 May

Do any of those work?

Rob

Hi Robert,

Wonderful we’re looking forward to hosting you on Tuesday, 21st March · 7:00 PM to 10:00 PM GMT at The Thirsty Bear.

To ensure the success and overall presentation quality of the discussion around Leveraged Trading, we would require two key visual materials:

An event banner (digital format) that visually presents the book, your name, and the event details. This will be used across our event page and in-room display.

A 60-second book teaser a short visual piece that introduces Leveraged Trading in a compelling way. This isn’t meant to be commercial advertising, but rather an atmospheric, professional visual that sets the intellectual tone before we move into discussion.

The teaser would ideally highlight the core themes of disciplined risk management, leverage, and decision-making under pressure visually reinforcing the mindset and frameworks explored in the book.

Warmly,

Ben Jarvis

Yes, he definitely hasn't read any of my books.

I’m not actually sure what an event banner (digital format) is. But I can do a singe page .pdf with a picture of me, and my book, and the date and time. Is that what you want?

Is a ‘short visual piece’ a video? If so, I don’t have the ability, budget or inclination to create a ‘professional visual’. I also don’t really have any idea how to ‘set an intellectual tone’, nor am I sure what one is. There are no ‘mindsets’ or ‘frameworks’ in the book. In fact I just did a text search and the word mindset doesn’t appear in the book at all. The word framework appears only once, in the phrase ‘regulatory framework‘. 

If you still want me to come, then let me know and I will prepare the ‘event banner’, but sorry no video.

Thanks

Rob

Hi Rob,

Thank you for your thoughtful reply, I really appreciate the clarity.

Yes, a single-page PDF with your photo, the Leveraged Trading cover, and the confirmed date and time would work perfectly as the event banner. That would be absolutely fine. Regarding the 60-second visual piece I completely understand your position. It is indeed a short video, and I appreciate that creating something professional may not be within your current scope or interest.

That said, the narrative prelude is an important part of how we structure our evenings. It serves as the opening piece on stage essentially the material that frames the discussion before we move into live dialogue. It’s less about marketing language or abstract “mindsets,” and more about visually introducing the world of the book the realities of leverage, risk, decision-making under uncertainty, and the professional discipline required in trading so the audience is properly situated before we begin.

Since you mentioned budget and logistics constraints, one option entirely without obligation would be to connect you with our production specialist. They work specifically with authors who don’t already have visual material and can create a concise, polished narrative prelude aligned with the tone of the event. You wouldn’t be committing to anything by speaking with them; it would simply be an exploratory conversation to see if it’s something you’d like to proceed with.

If you’re open to that introduction, I’d be happy to make the connection.

Looking forward to your thoughts.

Warmly,

Ben Jarvis

Good to know he appreciates the clarity. It annoys me when people don't.

Well, this is certainly sounding like a very professional event, there is an event banner, a video, a stage and a structured timetable. Must be a big private room in this pub. Secondly, this offer to connect me with a specialist... okay well it certainly is starting to smell a bit scammy. But I'm giving them the benefit of the doubt. 

OK I will send you the banner. But there will be no video: I have no interest in speaking to a production specialist but thank you for the offer. 

Can you confirm the date? You put Tuesday 21st March. Did you mean 31st March?

Rob

Yes, that is correct.

Warmly,

Ben Jarvis

All went quiet, but when I checked their website a few days ago it was showing this:

Bit weird, I am definitely not Yuri Olesha who apparently died 66 years ago. Let me check:

Just confirming I will see you Tuesday 7pm in the Thirsty Bear.

Rob

Yes, I’m looking forward to it. I also wanted to let you know that we’ve introduced a small participation fee. This supports a new feature where our readers will share their thoughts and reviews of the book on Amazon and Goodreads after the session.

If you’re still interested, I’d be happy to walk you through how the participation process works.

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

I assumed the participation fee was for the attendees... so I ignored the email.

By now I was confused, but I was thinking that maybe each evening is a double bill where they talk about some dead Russian dude for a bit, and then bring in a live British guy to liven things up.

Now for reasons of narrative exposition, I'm actually going to jump forward in time to Tuesday 31st March; in the evening, after I had been to the Thirsty Bear (that's the pub, remember), and I was on my way home

Me on the Tube after being to the Thirsty Bear (not really)

And whilst on the tube on the way home I did a little more digging (which yes, I should have done in advance), and boy oh boy, what did I find but a blog piece about an author being contacted by potential scam artists:

https://cynthiaelder.substack.com/p/author-beware-scams-abound

It's worth reading the whole article, but imagine how I felt when I read this part:

My name is Ben Jarvis, and I organize the Classics Book Club, where each month we spotlight books that spark meaningful conversation and connect readers to timeless stories.

Your novel, The Journey Begins (Tales of the Sea), with its rich historical detail, compelling family voices, and the sweeping backdrop of America on the brink of Civil War, perfectly captures the type of narrative our members love to explore. The blend of seafaring adventure, personal letters, and social upheaval offers countless themes for discussion.

Would you be interested in featuring The Journey Begins in our club? Our upcoming spotlight is scheduled for September 20, and I’d be delighted to reserve your feature spot."

And here is the punch line of the post:

There it is. The pitch. I concluded my little research project with a promise to reveal “Ben” and his so-called book club as a scam. It was worth $135 to share it with you.

And I also found this:

https://www.facebook.com/groups/1037926331701856/posts/1231399859021168/

So now you are probably thinking you know what happened last night. There was no pub, no Ben Jarvis, no bookclub, no stage, no event banner and no "framing of discussions before moving into live dialogue". Just a scammer using AI on the end of an email trying to scam authors around the world into sending them money for promotational videos, participation costs, and who knows what other tricks. An AI which thinks the 21st March 2026 is a Tuesday, presumably because of it's training data.

The truth is much stranger. 

There was a pub:

The Thirsty Bear - It exists

They sold Inches cider, so I purchased a pint.

And there was an upper floor; but not a private room, just a series of long trestle tables and groups of comfy chairs. And on one of those tables were sitting... the Classics London Book club age 20-45. Actual people. Not AI generated. Mostly men, with beards, but a couple of women without them. And they were talking about.... Yuri Olesha. And his book. Which apparently is very good (I haven't read it). That was all I got in terms of live dialogue or discussion framing. They did look at me oddly, as it was obvious I was an interloper. Mostly I sat quietly and did some research on portfolio optimisation. 

But there was no stage, no private room, no event banner... and certainly no Ben Jarvis. But the table in that pub had a 'reserved' sign on it. And the name on that reservation? You already know what it is. It was "Ben Jarvis". And when I arrived and asked, confused, which one of the people on the table was Ben Jarvis I got told (quite sharply I thought) "Oh, he isn't here yet". But I waited for an hour. And he didn't arrive. Though I emailed him numerous times - or at least I emailed the person I thought was Ben Jarvis. So I finished my pint, headed home, and then on the Tube did my Googling. You know the rest.

So my question is this, does Ben Jarvis exist? Is there a real Ben Jarvis, an innocent victim of this, who is being impersonated by some AI scammer; and who just happened to be (somewhat) late to last nights meeting?

Or this much more sinister? Is the 20-45 year old London book club just a front? The organisers invented this "Ben Jarvis" person, and go through the motions of talking about dead Russian authors once a month just so that if anyone checks there will be evidence of the book club's existence? Meanwhile, they go home every night and scam authors into sending money for copyediting or publishing. In which case, they made a foolish error to pick on someone who can easily travel to their meetings. That would explain why they were so annoyed when I asked where Ben was.

So if anyone from the 20-45 London book club is reading this, and especially if you are the real Ben Jarvis please feel free to get in touch with me so I can set the record straight.

That is the end of the original post, but after I put it up the story continued....

Firstly, a comment I made on the club discussion board pointing out that the club was being used to front a scam and linking to this post. Shortly after there was an update on the book club meetup page:

There goes my conspiracy theory! I have also messaged Ben Jarvis via the meetup system and I am waiting for a response (I assume this will be from the real Ben Jarvis unless things are very dark).

Meanwhile, I got another email from the original "Ben Jarvis":

Hello Robert, I'm very sorry for late response, I wasn't on sit (sic, means "site"?) yesterday but I'm sure my fellow organizer are there (sic, means "were there"?), and I'm sure your novel wasn't featured 

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

Terrible grammar and spelling. I think he has run out of AI tokens. Still, let's have some fun.

Hi Ben

There were people there, and as you say my book (not a novel) wasn't featured, so why did you ask me to come last night?

Rob

I mentioned earlier, before you attended the event last night, that a participation fee applies for featuring due to certain conditions, but I didn’t get a response from you.

Warmly,

Ben Jarvis

Hi Ben

Oh I didn't understand that I would have to pay the participation fee I assumed it would be the book club members.

Can I be featured at next months talk?

thanks

Rob

Yes, of course you can. Our next event is coming up on April 21st, so please let me know if you’ll be available.

Once your participation fee has been paid, we’ll set everything up on our end. We feature many authors each month, so registering early helps us prepare properly and secure your spot for the event.

I’d love to hear your thoughts.

Warmly,

Ben Jarvis

Hi Ben

Just a few questions. How much is the participation fee? How should I pay it? And why didn't you mention this when you first got in touch?

Also you say "You feature many authors each month" but there were not multiple authors featured last night, just discussion of one book by an author who wasn't there.

Also you said there would be a digital display, and a video, and a stage; but the venue clearly didn't have any of those facilities. It wasn't even a private room. Seems a bit odd.

Rob

And whilst waiting for a reply to that, I got an email from .... Ben Jarvis. This time via the meetup platform:

Obviously I had to let the other "Ben" know about this strange turn of events:

Hi Ben 

OK this is very weird. I have been contacted by someone claiming to be Ben Jarvis from the Classics book club. He said:

"Hi Robert, any communication by email from someone claiming to be a representative of the bookclub is a scam. We don't arrange events with contemporary writers and never contact authors directly. Regards, Ben."

But you say that you are Ben Jarvis from the book club? I don't understand. Please explain it to me.

Rob

That’s definitely not me, Robert. I’d like to know who this so-called Ben Jarvis is and how he got your email address to contact you.

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

How could I possibly respond to the sheer chutzpah of this scammer? How about this:

This is the weird thing. He contacted me via the meetup platform. So he definitely controls the account of the Ben Jarvis that runs the book club. I am assuming that is your meetup account. Could it have been hacked?! Perhaps you should change your password, and then contact me from that meetup account so I know it is you this time.

regards

Rob

PS Could you also answer the questions I asked earlier this afternoon?

How much is the participation fee? ...<questions repeat>

First, please block the Meetup account that contacted you for now until I sort things out on my end, as the account may have been hacked. 

Regarding the participation fee, it is $175, and payment is made via bank transfer. I will share my manager’s bank details with you so you can proceed.

I also understand your concern about this not being mentioned earlier. The reason is that we initially reach out to confirm an author’s interest and availability before discussing participation logistics. This helps us tailor the experience appropriately, as the structure and features of each session can vary depending on the level of involvement and presentation we plan for the book. That said, I appreciate your feedback and will ensure this is communicated more clearly upfront moving forward.

On the point about featuring multiple authors, you are absolutely right to notice the difference. While we do feature several authors each month overall, the format varies. Some sessions are dedicated to a single book for deeper, focused discussion, while others include multiple books, often with additional virtual (Zoom) sessions to accommodate broader participation.

Regarding the digital display, video, and stage elements, what we typically incorporate is a narrative prelude, a short 60–90 second book trailer designed to introduce the book to our readers in an engaging way before discussion begins. This helps set the tone, build context, and capture interest right from the start. For the last event, since it was a single-book focused session in a more intimate setting, we did not implement those facilities. However, they are part of what we are preparing to include in upcoming sessions, and we would ensure those elements are properly set up for your feature.

I hope this helps clarify everything, looking forward to your response.

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

$175 - it was only $135 in the US authors scam, so inflation is clearly hitting these guys hard.

Ok can I have the bank details please.

Thanks Rob 

Here are our manager account details:

 

 Account name

 Damilare Timothy Ayeni 

 Bank name

 Wells Fargo 

.....<redacted by me>

 Bank address

 651 N Broad St, Suite 206, Middletown ,19709 Delaware, US

Warmly,

Ben Jarvis

Organizer at Classics Book club London age 20-45

And there we have it. "Damilare Timothy Ayeni" is probably "Ben"s real name. Or at least certainly someone closely associated with him.

Time for the coup de grace:

Sorry "Ben" there is no money coming. You are a scammer and clearly not the real Ben Jarvis. And now I know your name, or at least the name of someone you are closely associated with. I'll be passing this information on to Wells Fargo and the US authorities.

You were quite plausible though, enough that I went along to the book club, though there were multiple red flags before then. You've clearly used AI to write nearly all of your messages. You have clearly no idea how book clubs typically work. 

But you made a mistake choosing to try and contact an author within easy traveling distance of London, since I could easily verify that you weren't who you said you were.

Unfortunately I was never going to hand over any money. You are making a mistake going after authors; publishing isn't a lucrative business. I make about $7 on average in royalties on every book I sell. Which is more than most. But it makes it very unlikely I will break even on a visit to a book club if I have to pay $175 plus my own costs. 

Although I would hope that you now turn to doing more productive things for society, if you want to continue scamming you had better pick another alias. A quick google search will now turn up a reference to your alias on my blog. Oh sorry, didn't I mention it, I've actually been documenting our conversation on my blog, here, in real time: https://qoppac.blogspot.com/2026/04/ben-jarvis-mysterious-london-book-club.html

This will be my last message and I don't imagine I will be hearing from you again. So best of luck. It's been a pleasure wasting your time.

regards

Rob

And that dear reader, is the end of my story. Good night.

Postscript:

The bank account address is also mentioned in this Facebook post: https://www.facebook.com/ansharazintha/posts/authors-beware-of-scammersquick-note-if-you-dont-want-to-plough-through-my-exper/850700774473334/

The article links to this useful post  for authors on being scammed.

Further googling reveals this particular bank account address is associated with quite a few publishing and other scams:

https://www.goodreads.com/topic/show/24081729-is-this-a-scam

https://www.tripadvisor.co.uk/ShowUserReviews-g34036-d19786714-r955918521-Ziyas-Middletown_Delaware.html